{
  "source_file": "0930",
  "source_platform": "研究机构",
  "author": "Dive into Deep Learning",
  "title_listed": "Dive into Deep Learning 主页",
  "keywords": "深度学习,机器学习,教程",
  "domain": "机器学习",
  "content_type": "书籍",
  "is_paid_flag": "否",
  "url": "https://www.d2l.ai/",
  "publish_date": "持续更新",
  "corpus_stage": "机器学习",
  "notes": "开源深度学习教材主页",
  "id": "db16d08cbae0",
  "collected_at": "2026-10-02T16:07:45",
  "title": "Dive into Deep Learning — Dive into Deep Learning 1.0.3 documentation",
  "body_markdown": "Table Of Contents\nDive into Deep Learning\n¶\nDive into Deep Learning\nInteractive\ndeep learning book with code, math, and discussions\nImplemented with\nPyTorch\n,\nNumPy/MXNet\n,\nJAX\n, and\nTensorFlow\nAdopted at 500 universities from 70 countries\nStar\nFollow @D2L_ai\n[Feb 2023]\n        The book is forthcoming on Cambridge University Press (\norder\n).\n        The Chinese version is the\nbest seller\nat the largest Chinese online bookstore.\n        Follow D2L's\nopen-source project\nfor the latest updates.\n[Dec 2022] JAX implementation is available! New topics of\nreinforcement learning\n,\nGaussian processes\n, and\nhyperparameter optimization\nare added!\n[Jul 2022] Check out our\nnew API\nfor implementation\n            and new topics like\n            generalization in\nclassification\nand\ndeep learning\n,\nResNeXt\n,\nCNN design space\n, and\n            transformers for\nvision\nand\nlarge-scale pretraining\n.\n[May 2022] Join\nus\nto improve ongoing translations\n          in\nPortuguese\n,\nTurkish\n,\nVietnamese\n,\nKorean\n,\n          and\nJapanese\n.\n[Dec 2021] We added a new option to\nrun this book\nfor free: check out\nSageMaker Studio Lab\n.\n[May 2021]\n      Slides, Jupyter notebooks, assignments, and videos of the Berkeley course can be found at the\nsyllabus page\n.\nAuthors\nAston Zhang\nAmazon\nZack C. Lipton\nCMU and Amazon\nMu Li\nAmazon\nAlex J. Smola\nAmazon\nVol.2 Chapter Authors\nPratik Chaudhari\nUPenn and Amazon\nReinforcement Learning\nRasool Fakoor\nAmazon\nReinforcement Learning\nKavosh Asadi\nAmazon\nReinforcement Learning\nAndrew Gordon Wilson\nNYU and Amazon\nGaussian Processes\nAaron Klein\nAmazon\nHyperparameter Optimization\nMatthias Seeger\nAmazon\nHyperparameter Optimization\nCedric Archambeau\nAmazon\nHyperparameter Optimization\nShuai Zhang\nAmazon\nRecommender Systems\nYi Tay\nGoogle\nRecommender Systems\nBrent Werness\nAmazon\nMathematics\n        for Deep Learning\nRachel Hu\nAmazon\nMathematics\n        for Deep Learning\nFramework Adaptation Authors\nAnirudh Dagar\nAmazon\nPyTorch Adaptation\nJAX Adaptation\nYuan Tang\nAkuity\nTensorFlow Adaptation\nWe thank all the\ncommunity contributors\nfor making this open source book better for everyone.\nContribute to the book\nEach section is an executable Jupyter notebook\nYou can modify the code and tune hyperparameters to get instant\n      feedback to accumulate practical experiences in deep learning.\nRun\nlocally\nAmazon SageMaker\nStudio Lab\nAmazon\nSageMaker\nGoogle\nColab\nMathematics + Figures + Code\nWe offer an interactive learning experience with mathematics, figures,\n  code, text, and discussions, where concepts and techniques are illustrated\n    and implemented with experiments on real data sets.\nActive\ncommunity\nsupport\nYou can discuss and learn with thousands of peers in the community\n        through the link provided in each section.\nD2L as a textbook or a reference book\n[+]\nClick here to show the incomplete list.\nAbasyn University, Islamabad Campus\nAlexandria University\nAmirkabir University of Technology\nAmity University\nAmrita Vishwa Vidyapeetham University\nAnna University\nAnna University Regional Campus Madurai\nAteneo de Naga University\nAustralian National University\nBar-Ilan University\nBarnard College\nBeijing Foresty University\nBirla Institute of Technology and Science, Hyderabad\nBirla Institute of Technology and Science, Pilani\nBML Munjal University\nBoston College\nBoston University\nBrac University\nBrandeis University\nBrown University\nBrunel University London\nCairo University\nCalifornia State University, Northridge\nCankaya University\nCarnegie Mellon University\nCenter for Research and Advanced Studies of the National Polytechnic Institute\nChalmers University of Technology\nChennai Mathematical Institute\nChouaib Doukkali University\nChulalongkorn University\nCity College of New York\nCity University of Hong Kong\nCity University of Science and Information Technology\nCollege of Engineering Pune\nColumbia University\nCornell University\nCyprus Institute\nDeakin University\nDiponegoro University\nDresden University of Technology\nDuke University\nDurban University of Technology\nEastern Mediterranean University\nEcole Nationale Supérieure d'Informatique\nEcole Nationale Supérieure de Cognitique\nÉcole Nationale Supérieure de Techniques Avancées\nEindhoven University of Technology\nEmory University\nEötvös Loránd University\nEscuela Politécnica Nacional\nEscuela Superior Politecnica del Litoral\nFederal University Lokoja\nFeng Chia University\nFisk University\nFlorida Atlantic University\nFPT University\nFudan University\nGanpat University\nGayatri Vidya Parishad College of Engineering (Autonomous)\nGazi Üniversitesi\nGdańsk University of Technology\nGeorge Mason University\nGeorgetown University\nGeorgia Institute of Technology\nGheorghe Asachi Technical University of Iaşi\nGolden Gate University\nGreat Lakes Institute of Management\nGwangju Institute of Science and Technology\nHabib University\nHamad Bin Khalifa University\nHangzhou Dianzi University\nHangzhou Dianzi University\nHankuk University of Foreign Studies\nHarare Institute of Technology\nHarbin Institute of Technology\nHarvard University\nHasso-Plattner-Institut\nHebrew University of Jerusalem\nHeinrich-Heine-Universität Düsseldorf\nHenan Institute of Technology\nHertie School\nHigher Institute of Applied Science and Technology of Sousse\nHiroshima University\nHo Chi Minh City University of Foreign Languages and Information Technology\nHochschule Bremen\nHochschule für Technik und Wirtschaft\nHochschule Hamm-Lippstadt\nHong Kong University of Science and Technology\nHouston Community College\nHuazhong University of Science and Technology\nHumboldt-Universität zu Berlin\nİbn Haldun Üniversitesi\nIcahn School of Medicine at Mount Sinai\nImperial College London\nIMT Mines Alès\nIndian Institute of Technology Bombay\nIndian Institute of Technology Hyderabad\nIndian Institute of Technology Jodhpur\nIndian Institute of Technology Kanpur\nIndian Institute of Technology Kharagpur\nIndian Institute of Technology Mandi\nIndian Institute of Technology Ropar\nIndian School of Business\nIndira Gandhi National Open University\nIndraprastha Institute of Information Technology, Delhi\nInstitut catholique d'arts et métiers (ICAM)\nInstitut de recherche en informatique de Toulouse\nInstitut Supérieur d'Informatique et des Techniques de Communication\nInstitut Supérieur De L'electronique Et Du Numérique\nInstitut Teknologi Bandung\nInstituto Federal de Educação, Ciência e Tecnologia de São Paulo, Campus Salto\nInstituto Politécnico Nacional\nInstituto Tecnológico Autónomo de México\nInstituto Tecnológico de Buenos Aires\nIslamic University of Medina\nİstanbul Teknik Üniversitesi\nIT-Universitetet i København\nIvan Franko National University of Lviv\nJeonbuk National Univerity\nJohns Hopkins University\nJulius-Maximilians-Universität Würzburg\nKeio University\nKing Abdullah University of Science and Technology\nKing Fahd University of Petroleum and Minerals\nKing Faisal University\nKongu Engineering College\nKorea Aerospace University\nKPR Institute of Engineering and Technology\nKyungpook National University\nLancaster University\nLeading Unviersity\nLeibniz Universität Hannover\nLeuphana University of Lüneburg\nLondon School of Economics & Political Science\nM.S.Ramaiah University of Applied Sciences\nMake School\nMasaryk University\nMassachusetts Institute of Technology\nMaynooth University\nMcGill University\nMenoufia University\nMilwaukee School of Engineering\nMinia University\nMississippi State University\nMissouri University of Science and Technology\nMohammad Ali Jinnah University\nMohammed V University in Rabat\nMonash University\nMultimedia University\nMurdoch University\nNanjing University\nNanchang Hangkong University\nNanjing Medical University\nNanjing University\nNational Chung Hsing University\nNational Institute of Technical Teachers Training & Research\nNational Institute of Technology Trichy\nNational Institute of Technology, Warangal\nNational Sun Yat-sen University\nNational Taichung University of Science and Technology\nNational Taiwan University\nNational Technical University of Athens\nNational Technical University of Ukraine\nNational United University\nNational University of Sciences and Technology\nNational University of Singapore\nNazarbayev University\nNew Jersey Institute of Technology\nNew Mexico Institute of Mining and Technology\nNew Mexico State University\nNew York University\nNewman University\nNorth Ossetian State University\nNorthCap University\nNortheastern University\nNorthwestern Polytechnical University\nNorthwestern University\nOhio University\nPakuan University\nPeking University\nPennsylvania State University\nPohang University of Science and Technology\nPolitechnika Białostocka\nPolitecnico di Milano\nPoliteknik Negeri Semarang\nPomona College\nPontificia Universidad Católica de Chile\nPontificia Universidad Católica del Perú\nPortland State University\nPunjabi University\nPurdue University\nPurdue University Northwest\nQuaid-e-Azam University\nQueen Mary University of London\nQueen's University\nRadboud Universiteit\nRadboud University\nRajiv Gandhi Institute of Petroleum Technology\nRensselaer Polytechnic Institute\nRowan University\nRutgers, The State University of New Jersey\nRVS Institute of Management Studies and Research\nRWTH Aachen University\nSant Longowal Institute of Engineering Technology\nSanta Clara University\nSapienza Università di Roma\nSeoul National University\nSeoul National University of Science and Technology\nShanghai Jiao Tong University\nShanghai University of Electric Power\nShanghai University of Finance and Economics\nShantilal Shah Engineering College\nSharif University of Technology\nShenzhen University\nShivaji University, Kolhapur\nSimon Fraser University\nSingapore University of Technology and Design\nSogang University\nSookmyung Women's University\nSouthern Connecticut State University\nSouthern New Hampshire University\nSt. Pölten University of Applied Sciences\nStanford University\nState University of New York at Albany\nState University of New York at Binghamton\nState University of New York at Fredonia\nStellenbosch University\nStevens Institute of Technology\nSungkyunkwan University\nTechnion - Israel Institute of Technology\nTechnische Universität Berlin\nTechnische Universität München\nTechnische Universiteit Delft\nTecnológico de Monterrey, Campus Guadalajara\nTekirdağ Namık Kemal Üniversitesi\nTélécom Paris\nTelkom University\nTexas A&M University\nThapar Institute of Engineering and Technology\nTsinghua University\nTufts University\nUmeå University\nUniversidad Carlos III de Madrid\nUniversidad de Ibagué\nUniversidad de Ingeniería y Tecnología - UTEC\nUniversidad de Salamanca\nUniversidad de Zaragoza\nUniversidad del Norte, Colombia\nUniversidad Icesi\nUniversidad Militar Nueva Granada\nUniversidad Nacional Agraria La Molina\nUniversidad Nacional Autónoma de México\nUniversidad Nacional de Colombia Sede Manizales\nUniversidad Nacional de Tierra del Fuego\nUniversidad Politécnica de Chiapas\nUniversidad Politécnica de Valencia\nUniversidad Politécnica Salesiana, Cuenca\nUniversidad Rafael Landivar\nUniversidad Rey Juan Carlos\nUniversidad San Francisco de Quito\nUniversidad Tecnológica de Pereira\nUniversidad Tecnológica Nacional\nUniversidade Católica de Brasília\nUniversidade Estadual de Campinas\nUniversidade Federal de Goiás\nUniversidade Federal de Minas Gerais\nUniversidade Federal de Ouro Preto\nUniversidade Federal de Pernambuco\nUniversidade Federal de São Carlos\nUniversidade Federal de Viçosa\nUniversidade Federal do Pampa\nUniversidade Federal do Rio Grande\nUniversidade NOVA de Lisboa\nUniversidade Presbiteriana Mackenzie\nUniversidade Tecnológica Federal do Paraná\nUniversità Cattolica del Sacro Cuore\nUniversità degli Studi di Bari Aldo Moro\nUniversità degli Studi di Brescia\nUniversità degli Studi di Catania\nUniversità degli Studi di Padova\nUniversitas Andalas, Padang\nUniversitas Indonesia\nUniversitas Negeri Yogyakarta\nUniversitas Udayana\nUniversität Bremen\nUniversitat de Barcelona\nUniversitat de València\nUniversität Heidelberg\nUniversität Leipzig\nUniversitat Politècnica de Catalunya\nUniversitatea Babeș-Bolyai\nUniversitatea de Vest din Timișoara\nUniversité Abderrahmane Mira de Béjaïa\nUniversité Clermont Auvergne\nUniversité Côte d'Azur\nUniversité de Caen Normandie\nUniversité de Rouen Normandie\nUniversité de technologie de Compiègne\nUniversité Paris-Saclay\nUniversité Toulouse 1 Capitole\nUniversity of Akron\nUniversity of Alabama in Huntsville\nUniversity of Allahabad\nUniversity of Applied Sciences Würzburg-Schweinfurt\nUniversity of Arkansas\nUniversity of Augsburg\nUniversity of Baghdad\nUniversity of Bath\nUniversity of Bordj Bou Arreridj\nUniversity of British Columbia\nUniversity of California, Berkeley\nUniversity of California, Irvine\nUniversity of California, Los Angeles\nUniversity of California, San Diego\nUniversity of California, Santa Barbara\nUniversity of California, Santa Cruz\nUniversity of Cambridge\nUniversity of Canberra\nUniversity of Catania\nUniversity of Cincinnati\nUniversity of Colorado Boulder\nUniversity of Connecticut\nUniversity of Copenhagen\nUniversity of Derby\nUniversity of Florida\nUniversity of Genoa\nUniversity of Ghana\nUniversity of Groningen\nUniversity of Hamburg\nUniversity of Houston\nUniversity of Hull\nUniversity of Iceland\nUniversity of Idaho\nUniversity of Illinois at Urbana-Champaign\nUniversity of International Business and Economics\nUniversity of Klagenfurt\nUniversity of Liège\nUniversity of Louisiana at Lafayette\nUniversity of Maryland\nUniversity of Maryland Baltimore County\nUniversity of Massachusetts Lowell\nUniversity of Michigan\nUniversity of Michigan Dearborn\nUniversity of Milano-Bicocca\nUniversity of Minnesota, Twin Cities\nUniversity of Moratuwa\nUniversity of Nebraska Omaha\nUniversity of New Hampshire\nUniversity of Newcastle\nUniversity of North Carolina at Chapel Hill\nUniversity of North Texas\nUniversity of Northern Philippines\nUniversity of Nottingham\nUniversity of Oslo\nUniversity of Pennsylvania\nUniversity of Pittsburgh\nUniversity of Rostock\nUniversity of São Paulo\nUniversity of Science and Technology of China\nUniversity of Southern California\nUniversity of Southern Maine\nUniversity of St Andrews\nUniversity of St. Thomas\nUniversity of Suffolk\nUniversity of Sydney\nUniversity of Szeged\nUniversity of Technology Sydney\nUniversity of Tehran\nUniversity of Texas at Austin\nUniversity of Texas at Dallas\nUniversity of Texas Rio Grande Valley\nUniversity of Udine\nUniversity of Warsaw\nUniversity of Washington\nUniversity of Waterloo\nUniversity of Wisconsin Madison\nUniverzita Komenského v Bratislave\nUniwersytet Jagielloński\nVardhaman College of Engineering\nVardhman Mahaveer Open University\nVietnamese-German University\nVignana Jyothi Institute Of Management\nVilnius University\nWageningen University\nWest Virginia University\nWestern University\nWichita State University\nXavier University Bhubaneswar\nXi'an Jiaotong Liverpool University\nXiamen University\nXianning Vocational Technical College\nYale University\nYeshiva University\nYıldız Teknik Üniversitesi\nYonsei University\nYunnan University\nZhejiang University\nBibTeX entry for citing the book\n@book{zhang2023dive,\n    title={Dive into Deep Learning},\n    author={Zhang, Aston and Lipton, Zachary C. and Li, Mu and Smola, Alexander J.},\n    publisher={Cambridge University Press},\n    note={\\url{https://D2L.ai}},\n    year={2023}\n}\nTable of contents\nPreface\nInstallation\nNotation\n1. Introduction\n1.1. A Motivating Example\n1.2. Key Components\n1.3. Kinds of Machine Learning Problems\n1.4. Roots\n1.5. The Road to Deep Learning\n1.6. Success Stories\n1.7. The Essence of Deep Learning\n1.8. Summary\n1.9. Exercises\n2. Preliminaries\n2.1. Data Manipulation\n2.2. Data Preprocessing\n2.3. Linear Algebra\n2.4. Calculus\n2.5. Automatic Differentiation\n2.6. Probability and Statistics\n2.7. Documentation\n3. Linear Neural Networks for Regression\n3.1. Linear Regression\n3.2. Object-Oriented Design for Implementation\n3.3. Synthetic Regression Data\n3.4. Linear Regression Implementation from Scratch\n3.5. Concise Implementation of Linear Regression\n3.6. Generalization\n3.7. Weight Decay\n4. Linear Neural Networks for Classification\n4.1. Softmax Regression\n4.2. The Image Classification Dataset\n4.3. The Base Classification Model\n4.4. Softmax Regression Implementation from Scratch\n4.5. Concise Implementation of Softmax Regression\n4.6. Generalization in Classification\n4.7. Environment and Distribution Shift\n5. Multilayer Perceptrons\n5.1. Multilayer Perceptrons\n5.2. Implementation of Multilayer Perceptrons\n5.3. Forward Propagation, Backward Propagation, and Computational Graphs\n5.4. Numerical Stability and Initialization\n5.5. Generalization in Deep Learning\n5.6. Dropout\n5.7. Predicting House Prices on Kaggle\n6. Builders’ Guide\n6.1. Layers and Modules\n6.2. Parameter Management\n6.3. Parameter Initialization\n6.4. Lazy Initialization\n6.5. Custom Layers\n6.6. File I/O\n6.7. GPUs\n7. Convolutional Neural Networks\n7.1. From Fully Connected Layers to Convolutions\n7.2. Convolutions for Images\n7.3. Padding and Stride\n7.4. Multiple Input and Multiple Output Channels\n7.5. Pooling\n7.6. Convolutional Neural Networks (LeNet)\n8. Modern Convolutional Neural Networks\n8.1. Deep Convolutional Neural Networks (AlexNet)\n8.2. Networks Using Blocks (VGG)\n8.3. Network in Network (NiN)\n8.4. Multi-Branch Networks (GoogLeNet)\n8.5. Batch Normalization\n8.6. Residual Networks (ResNet) and ResNeXt\n8.7. Densely Connected Networks (DenseNet)\n8.8. Designing Convolution Network Architectures\n9. Recurrent Neural Networks\n9.1. Working with Sequences\n9.2. Converting Raw Text into Sequence Data\n9.3. Language Models\n9.4. Recurrent Neural Networks\n9.5. Recurrent Neural Network Implementation from Scratch\n9.6. Concise Implementation of Recurrent Neural Networks\n9.7. Backpropagation Through Time\n10. Modern Recurrent Neural Networks\n10.1. Long Short-Term Memory (LSTM)\n10.2. Gated Recurrent Units (GRU)\n10.3. Deep Recurrent Neural Networks\n10.4. Bidirectional Recurrent Neural Networks\n10.5. Machine Translation and the Dataset\n10.6. The Encoder–Decoder Architecture\n10.7. Sequence-to-Sequence Learning for Machine Translation\n10.8. Beam Search\n11. Attention Mechanisms and Transformers\n11.1. Queries, Keys, and Values\n11.2. Attention Pooling by Similarity\n11.3. Attention Scoring Functions\n11.4. The Bahdanau Attention Mechanism\n11.5. Multi-Head Attention\n11.6. Self-Attention and Positional Encoding\n11.7. The Transformer Architecture\n11.8. Transformers for Vision\n11.9. Large-Scale Pretraining with Transformers\n12. Optimization Algorithms\n12.1. Optimization and Deep Learning\n12.2. Convexity\n12.3. Gradient Descent\n12.4. Stochastic Gradient Descent\n12.5. Minibatch Stochastic Gradient Descent\n12.6. Momentum\n12.7. Adagrad\n12.8. RMSProp\n12.9. Adadelta\n12.10. Adam\n12.11. Learning Rate Scheduling\n13. Computational Performance\n13.1. Compilers and Interpreters\n13.2. Asynchronous Computation\n13.3. Automatic Parallelism\n13.4. Hardware\n13.5. Training on Multiple GPUs\n13.6. Concise Implementation for Multiple GPUs\n13.7. Parameter Servers\n14. Computer Vision\n14.1. Image Augmentation\n14.2. Fine-Tuning\n14.3. Object Detection and Bounding Boxes\n14.4. Anchor Boxes\n14.5. Multiscale Object Detection\n14.6. The Object Detection Dataset\n14.7. Single Shot Multibox Detection\n14.8. Region-based CNNs (R-CNNs)\n14.9. Semantic Segmentation and the Dataset\n14.10. Transposed Convolution\n14.11. Fully Convolutional Networks\n14.12. Neural Style Transfer\n14.13. Image Classification (CIFAR-10) on Kaggle\n14.14. Dog Breed Identification (ImageNet Dogs) on Kaggle\n15. Natural Language Processing: Pretraining\n15.1. Word Embedding (word2vec)\n15.2. Approximate Training\n15.3. The Dataset for Pretraining Word Embeddings\n15.4. Pretraining word2vec\n15.5. Word Embedding with Global Vectors (GloVe)\n15.6. Subword Embedding\n15.7. Word Similarity and Analogy\n15.8. Bidirectional Encoder Representations from Transformers (BERT)\n15.9. The Dataset for Pretraining BERT\n15.10. Pretraining BERT\n16. Natural Language Processing: Applications\n16.1. Sentiment Analysis and the Dataset\n16.2. Sentiment Analysis: Using Recurrent Neural Networks\n16.3. Sentiment Analysis: Using Convolutional Neural Networks\n16.4. Natural Language Inference and the Dataset\n16.5. Natural Language Inference: Using Attention\n16.6. Fine-Tuning BERT for Sequence-Level and Token-Level Applications\n16.7. Natural Language Inference: Fine-Tuning BERT\n17. Reinforcement Learning\n17.1. Markov Decision Process (MDP)\n17.2. Value Iteration\n17.3. Q-Learning\n18. Gaussian Processes\n18.1. Introduction to Gaussian Processes\n18.2. Gaussian Process Priors\n18.3. Gaussian Process Inference\n19. Hyperparameter Optimization\n19.1. What Is Hyperparameter Optimization?\n19.2. Hyperparameter Optimization API\n19.3. Asynchronous Random Search\n19.4. Multi-Fidelity Hyperparameter Optimization\n19.5. Asynchronous Successive Halving\n20. Generative Adversarial Networks\n20.1. Generative Adversarial Networks\n20.2. Deep Convolutional Generative Adversarial Networks\n21. Recommender Systems\n21.1. Overview of Recommender Systems\n21.2. The MovieLens Dataset\n21.3. Matrix Factorization\n21.4. AutoRec: Rating Prediction with Autoencoders\n21.5. Personalized Ranking for Recommender Systems\n21.6. Neural Collaborative Filtering for Personalized Ranking\n21.7. Sequence-Aware Recommender Systems\n21.8. Feature-Rich Recommender Systems\n21.9. Factorization Machines\n21.10. Deep Factorization Machines\n22. Appendix: Mathematics for Deep Learning\n22.1. Geometry and Linear Algebraic Operations\n22.2. Eigendecompositions\n22.3. Single Variable Calculus\n22.4. Multivariable Calculus\n22.5. Integral Calculus\n22.6. Random Variables\n22.7. Maximum Likelihood\n22.8. Distributions\n22.9. Naive Bayes\n22.10. Statistics\n22.11. Information Theory\n23. Appendix: Tools for Deep Learning\n23.1. Using Jupyter Notebooks\n23.2. Using Amazon SageMaker\n23.3. Using AWS EC2 Instances\n23.4. Using Google Colab\n23.5. Selecting Servers and GPUs\n23.6. Contributing to This Book\n23.7. Utility Functions and Classes\n23.8. The\nd2l\nAPI Document\nReferences\nNext\nPreface",
  "metadata": {
    "title": "Dive into Deep Learning — Dive into Deep Learning 1.0.3 documentation",
    "description": null,
    "keywords": null,
    "author": null
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [
    {
      "file": "attachments/db16d08cbae0/code/body-000.txt",
      "chars": 237,
      "language": "text"
    }
  ],
  "images": [
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_static/logo-with-text.png",
      "bytes": 87175,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-509f124ba61493e64845.png",
      "src": "https://www.d2l.ai/_static/logo-with-text.png",
      "alt": "Dive into Deep Learning",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/front-cup.jpg",
      "bytes": 86139,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-6e7ae4a93a7ee67230f5.jpg",
      "src": "https://www.d2l.ai/_images/front-cup.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/aston.jpg",
      "bytes": 35586,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-61b227df7fd82e1b0b88.jpg",
      "src": "https://www.d2l.ai/_images/aston.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/zack.jpg",
      "bytes": 24575,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-aff0af70847a3255018c.jpg",
      "src": "https://www.d2l.ai/_images/zack.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/mu.jpg",
      "bytes": 13518,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-52bb335d628350b3fd41.jpg",
      "src": "https://www.d2l.ai/_images/mu.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/alex.jpg",
      "bytes": 25199,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-086a70be1538b7964589.jpg",
      "src": "https://www.d2l.ai/_images/alex.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/pratik.jpg",
      "bytes": 49540,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-77ed4a38f8e68d1a11af.jpg",
      "src": "https://www.d2l.ai/_images/pratik.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/rasool.jpg",
      "bytes": 15620,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-4fb2f4ea094440f3d78c.jpg",
      "src": "https://www.d2l.ai/_images/rasool.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/kavosh.jpg",
      "bytes": 5941,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-f1cc94db29aafa5fa567.jpg",
      "src": "https://www.d2l.ai/_images/kavosh.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/andrew.jpg",
      "bytes": 43464,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-e480bacdb049be92a003.jpg",
      "src": "https://www.d2l.ai/_images/andrew.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/aaron.jpg",
      "bytes": 8200,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-0f09d254edef404c50fe.jpg",
      "src": "https://www.d2l.ai/_images/aaron.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/matthias.jpg",
      "bytes": 35364,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-1c415148d95a171c17c2.jpg",
      "src": "https://www.d2l.ai/_images/matthias.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/cedric.png",
      "bytes": 74861,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-f35c43ff66bee08ec7e0.png",
      "src": "https://www.d2l.ai/_images/cedric.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/shuai.jpg",
      "bytes": 17774,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-94ffcd98189dc5503e9b.jpg",
      "src": "https://www.d2l.ai/_images/shuai.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/yi.jpg",
      "bytes": 11892,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-622c5e72387bafa49f52.jpg",
      "src": "https://www.d2l.ai/_images/yi.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/brent.jpg",
      "bytes": 16126,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-8bba843f498dd8254460.jpg",
      "src": "https://www.d2l.ai/_images/brent.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/rachel.jpeg",
      "bytes": 9598,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-984914455e9dc5378c63.jpeg",
      "src": "https://www.d2l.ai/_images/rachel.jpeg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/anirudh.jpg",
      "bytes": 6326,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-760734a149b19f499b95.jpg",
      "src": "https://www.d2l.ai/_images/anirudh.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/yuan.jpg",
      "bytes": 9503,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-33573254acb3a2201c8c.jpg",
      "src": "https://www.d2l.ai/_images/yuan.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/laptop_jupyter.png",
      "bytes": 22855,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-43c1f444c24353465277.png",
      "src": "https://www.d2l.ai/_images/laptop_jupyter.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/sagemaker-studio-lab.png",
      "bytes": 2215,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-47b3f1cc747dbd67c34c.png",
      "src": "https://www.d2l.ai/_images/logos/sagemaker-studio-lab.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/sagemaker.png",
      "bytes": 43668,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-7c04a2f3122084a626a7.png",
      "src": "https://www.d2l.ai/_images/logos/sagemaker.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/colab.png",
      "bytes": 9402,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-0c1108f8bf5d38cd175f.png",
      "src": "https://www.d2l.ai/_images/logos/colab.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/notebook.gif",
      "bytes": 1830991,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-9a93ff452afcd150db78.gif",
      "src": "https://www.d2l.ai/_images/notebook.gif",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/eq.jpg",
      "bytes": 78001,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-7191716028af99ef5e27.jpg",
      "src": "https://www.d2l.ai/_images/eq.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/figure.jpg",
      "bytes": 59351,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-40356686598b7cdcccce.jpg",
      "src": "https://www.d2l.ai/_images/figure.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/code.jpg",
      "bytes": 43472,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-44d7e41af9f4cef30960.jpg",
      "src": "https://www.d2l.ai/_images/code.jpg",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/forum.gif",
      "bytes": 4032286,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-6e9f1df27f58443d71b1.gif",
      "src": "https://www.d2l.ai/_images/forum.gif",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg1.png",
      "bytes": 532753,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-731838933c3722549b50.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg1.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg2.png",
      "bytes": 437017,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-6b6f91603d7d3deb1ccf.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg2.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg3.png",
      "bytes": 453587,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-ce8c45efa2d4ed4bb392.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg3.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg4.png",
      "bytes": 449440,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-b8434f391a016bd42567.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg4.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg5.png",
      "bytes": 490397,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-d1c1af67976fdca9791b.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg5.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg6.png",
      "bytes": 472201,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-1f1a9e4f4b6ba078d47b.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg6.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/logos/logoimg7.png",
      "bytes": 329566,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-944b20113edf3f8aac9f.png",
      "src": "https://www.d2l.ai/_images/logos/logoimg7.png",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://www.d2l.ai/_images/map.png",
      "bytes": 4806712,
      "reused": false,
      "local_path": "attachments/db16d08cbae0/images/body-50a30cce390904f10632.png",
      "src": "https://www.d2l.ai/_images/map.png",
      "alt": "",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [],
  "links": [
    {
      "href": "https://www.amazon.com/Dive-into-Learning-Aston-Zhang/dp/1009389432/",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://github.com/d2l-ai/d2l-en",
      "label": "Star",
      "type": "a"
    },
    {
      "href": "https://twitter.com/D2L_ai?ref_src=twsrc%5Etfw",
      "label": "Follow @D2L_ai",
      "type": "a"
    },
    {
      "href": "https://raw.githubusercontent.com/d2l-ai/d2l-zh/master/static/frontpage/_images/sales/jd-2023020304-all-ai-zh-4.png",
      "label": "best seller",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_reinforcement-learning/index.html",
      "label": "reinforcement learning",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_gaussian-processes/index.html",
      "label": "Gaussian processes",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_hyperparameter-optimization/index.html",
      "label": "hyperparameter optimization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/oo-design.html",
      "label": "new API",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/generalization-classification.html",
      "label": "classification",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/generalization-deep.html",
      "label": "deep learning",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/resnet.html",
      "label": "ResNeXt",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/cnn-design.html",
      "label": "CNN design space",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/vision-transformer.html",
      "label": "vision",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/large-pretraining-transformers.html",
      "label": "large-scale pretraining",
      "type": "a"
    },
    {
      "href": "https://github.com/d2l-ai",
      "label": "us",
      "type": "a"
    },
    {
      "href": "https://pt.d2l.ai/",
      "label": "Portuguese",
      "type": "a"
    },
    {
      "href": "https://tr.d2l.ai/",
      "label": "Turkish",
      "type": "a"
    },
    {
      "href": "https://d2l.aivivn.com/",
      "label": "Vietnamese",
      "type": "a"
    },
    {
      "href": "https://ko.d2l.ai/",
      "label": "Korean",
      "type": "a"
    },
    {
      "href": "https://ja.d2l.ai/",
      "label": "Japanese",
      "type": "a"
    },
    {
      "href": "https://studiolab.sagemaker.aws/import/github/d2l-ai/d2l-pytorch-sagemaker-studio-lab/blob/main/GettingStarted-D2L.ipynb",
      "label": "SageMaker Studio Lab",
      "type": "a"
    },
    {
      "href": "https://courses.d2l.ai/berkeley-stat-157/syllabus.html",
      "label": "syllabus page",
      "type": "a"
    },
    {
      "href": "https://www.astonzhang.com/",
      "label": "Aston Zhang",
      "type": "a"
    },
    {
      "href": "http://zacklipton.com/",
      "label": "Zack C. Lipton",
      "type": "a"
    },
    {
      "href": "https://www.cs.cmu.edu/~muli/",
      "label": "Mu Li",
      "type": "a"
    },
    {
      "href": "https://alex.smola.org/",
      "label": "Alex J. Smola",
      "type": "a"
    },
    {
      "href": "https://pratikac.github.io/",
      "label": "Pratik Chaudhari",
      "type": "a"
    },
    {
      "href": "https://sites.google.com/site/rfakoor",
      "label": "Rasool Fakoor",
      "type": "a"
    },
    {
      "href": "https://cs.brown.edu/~kasadiat/",
      "label": "Kavosh Asadi",
      "type": "a"
    },
    {
      "href": "https://cims.nyu.edu/~andrewgw/",
      "label": "Andrew Gordon Wilson",
      "type": "a"
    },
    {
      "href": "https://aaronkl.github.io/",
      "label": "Aaron Klein",
      "type": "a"
    },
    {
      "href": "https://mseeger.github.io/",
      "label": "Matthias Seeger",
      "type": "a"
    },
    {
      "href": "http://www0.cs.ucl.ac.uk/staff/c.archambeau/",
      "label": "Cedric Archambeau",
      "type": "a"
    },
    {
      "href": "https://shuaizhang.tech/",
      "label": "Shuai Zhang",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/index.html",
      "label": "Recommender Systems",
      "type": "a"
    },
    {
      "href": "https://vanzytay.github.io/",
      "label": "Yi Tay",
      "type": "a"
    },
    {
      "href": "https://www.linkedin.com/in/brent-werness-1506471b7/",
      "label": "Brent Werness",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/index.html",
      "label": "Mathematics\n        for Deep Learning",
      "type": "a"
    },
    {
      "href": "https://www.linkedin.com/in/rachelsonghu/",
      "label": "Rachel Hu",
      "type": "a"
    },
    {
      "href": "https://github.com/AnirudhDagar",
      "label": "Anirudh Dagar",
      "type": "a"
    },
    {
      "href": "https://terrytangyuan.github.io/about/",
      "label": "Yuan Tang",
      "type": "a"
    },
    {
      "href": "https://github.com/d2l-ai/d2l-en/graphs/contributors",
      "label": "community contributors",
      "type": "a"
    },
    {
      "href": "https://d2l.ai/chapter_appendix-tools-for-deep-learning/contributing.html",
      "label": "Contribute to the book",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_installation/index.html",
      "label": "Run locally",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/sagemaker.html",
      "label": "Amazon SageMaker",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/colab.html",
      "label": "Google Colab",
      "type": "a"
    },
    {
      "href": "https://discuss.d2l.ai/c/5",
      "label": "community",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preface/index.html",
      "label": "Preface",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_notation/index.html",
      "label": "Notation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_introduction/index.html",
      "label": "1. Introduction",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/index.html",
      "label": "2. Preliminaries",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/ndarray.html",
      "label": "2.1. Data Manipulation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/pandas.html",
      "label": "2.2. Data Preprocessing",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/linear-algebra.html",
      "label": "2.3. Linear Algebra",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/calculus.html",
      "label": "2.4. Calculus",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/autograd.html",
      "label": "2.5. Automatic Differentiation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/probability.html",
      "label": "2.6. Probability and Statistics",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_preliminaries/lookup-api.html",
      "label": "2.7. Documentation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/index.html",
      "label": "3. Linear Neural Networks for Regression",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/linear-regression.html",
      "label": "3.1. Linear Regression",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/synthetic-regression-data.html",
      "label": "3.3. Synthetic Regression Data",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/linear-regression-scratch.html",
      "label": "3.4. Linear Regression Implementation from Scratch",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/linear-regression-concise.html",
      "label": "3.5. Concise Implementation of Linear Regression",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/generalization.html",
      "label": "3.6. Generalization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-regression/weight-decay.html",
      "label": "3.7. Weight Decay",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/index.html",
      "label": "4. Linear Neural Networks for Classification",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/softmax-regression.html",
      "label": "4.1. Softmax Regression",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/image-classification-dataset.html",
      "label": "4.2. The Image Classification Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/classification.html",
      "label": "4.3. The Base Classification Model",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/softmax-regression-scratch.html",
      "label": "4.4. Softmax Regression Implementation from Scratch",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/softmax-regression-concise.html",
      "label": "4.5. Concise Implementation of Softmax Regression",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_linear-classification/environment-and-distribution-shift.html",
      "label": "4.7. Environment and Distribution Shift",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/index.html",
      "label": "5. Multilayer Perceptrons",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/mlp.html",
      "label": "5.1. Multilayer Perceptrons",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/mlp-implementation.html",
      "label": "5.2. Implementation of Multilayer Perceptrons",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/backprop.html",
      "label": "5.3. Forward Propagation, Backward Propagation, and Computational Graphs",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/numerical-stability-and-init.html",
      "label": "5.4. Numerical Stability and Initialization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/dropout.html",
      "label": "5.6. Dropout",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_multilayer-perceptrons/kaggle-house-price.html",
      "label": "5.7. Predicting House Prices on Kaggle",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/index.html",
      "label": "6. Builders’ Guide",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/model-construction.html",
      "label": "6.1. Layers and Modules",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/parameters.html",
      "label": "6.2. Parameter Management",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/init-param.html",
      "label": "6.3. Parameter Initialization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/lazy-init.html",
      "label": "6.4. Lazy Initialization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/custom-layer.html",
      "label": "6.5. Custom Layers",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/read-write.html",
      "label": "6.6. File I/O",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_builders-guide/use-gpu.html",
      "label": "6.7. GPUs",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/index.html",
      "label": "7. Convolutional Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/why-conv.html",
      "label": "7.1. From Fully Connected Layers to Convolutions",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/conv-layer.html",
      "label": "7.2. Convolutions for Images",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/padding-and-strides.html",
      "label": "7.3. Padding and Stride",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/channels.html",
      "label": "7.4. Multiple Input and Multiple Output Channels",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/pooling.html",
      "label": "7.5. Pooling",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-neural-networks/lenet.html",
      "label": "7.6. Convolutional Neural Networks (LeNet)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/index.html",
      "label": "8. Modern Convolutional Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/alexnet.html",
      "label": "8.1. Deep Convolutional Neural Networks (AlexNet)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/vgg.html",
      "label": "8.2. Networks Using Blocks (VGG)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/nin.html",
      "label": "8.3. Network in Network (NiN)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/googlenet.html",
      "label": "8.4. Multi-Branch Networks (GoogLeNet)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/batch-norm.html",
      "label": "8.5. Batch Normalization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_convolutional-modern/densenet.html",
      "label": "8.7. Densely Connected Networks (DenseNet)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/index.html",
      "label": "9. Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/sequence.html",
      "label": "9.1. Working with Sequences",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/text-sequence.html",
      "label": "9.2. Converting Raw Text into Sequence Data",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/language-model.html",
      "label": "9.3. Language Models",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/rnn.html",
      "label": "9.4. Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/rnn-scratch.html",
      "label": "9.5. Recurrent Neural Network Implementation from Scratch",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/rnn-concise.html",
      "label": "9.6. Concise Implementation of Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-neural-networks/bptt.html",
      "label": "9.7. Backpropagation Through Time",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/index.html",
      "label": "10. Modern Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/lstm.html",
      "label": "10.1. Long Short-Term Memory (LSTM)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/gru.html",
      "label": "10.2. Gated Recurrent Units (GRU)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/deep-rnn.html",
      "label": "10.3. Deep Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/bi-rnn.html",
      "label": "10.4. Bidirectional Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/machine-translation-and-dataset.html",
      "label": "10.5. Machine Translation and the Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/encoder-decoder.html",
      "label": "10.6. The Encoder–Decoder Architecture",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/seq2seq.html",
      "label": "10.7. Sequence-to-Sequence Learning for Machine Translation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recurrent-modern/beam-search.html",
      "label": "10.8. Beam Search",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/index.html",
      "label": "11. Attention Mechanisms and Transformers",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/queries-keys-values.html",
      "label": "11.1. Queries, Keys, and Values",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/attention-pooling.html",
      "label": "11.2. Attention Pooling by Similarity",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/attention-scoring-functions.html",
      "label": "11.3. Attention Scoring Functions",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/bahdanau-attention.html",
      "label": "11.4. The Bahdanau Attention Mechanism",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/multihead-attention.html",
      "label": "11.5. Multi-Head Attention",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/self-attention-and-positional-encoding.html",
      "label": "11.6. Self-Attention and Positional Encoding",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_attention-mechanisms-and-transformers/transformer.html",
      "label": "11.7. The Transformer Architecture",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/index.html",
      "label": "12. Optimization Algorithms",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/optimization-intro.html",
      "label": "12.1. Optimization and Deep Learning",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/convexity.html",
      "label": "12.2. Convexity",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/gd.html",
      "label": "12.3. Gradient Descent",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/sgd.html",
      "label": "12.4. Stochastic Gradient Descent",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/minibatch-sgd.html",
      "label": "12.5. Minibatch Stochastic Gradient Descent",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/momentum.html",
      "label": "12.6. Momentum",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/adagrad.html",
      "label": "12.7. Adagrad",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/rmsprop.html",
      "label": "12.8. RMSProp",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/adadelta.html",
      "label": "12.9. Adadelta",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/adam.html",
      "label": "12.10. Adam",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_optimization/lr-scheduler.html",
      "label": "12.11. Learning Rate Scheduling",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/index.html",
      "label": "13. Computational Performance",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/hybridize.html",
      "label": "13.1. Compilers and Interpreters",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/async-computation.html",
      "label": "13.2. Asynchronous Computation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/auto-parallelism.html",
      "label": "13.3. Automatic Parallelism",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/hardware.html",
      "label": "13.4. Hardware",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/multiple-gpus.html",
      "label": "13.5. Training on Multiple GPUs",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/multiple-gpus-concise.html",
      "label": "13.6. Concise Implementation for Multiple GPUs",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computational-performance/parameterserver.html",
      "label": "13.7. Parameter Servers",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/index.html",
      "label": "14. Computer Vision",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/image-augmentation.html",
      "label": "14.1. Image Augmentation",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/fine-tuning.html",
      "label": "14.2. Fine-Tuning",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/bounding-box.html",
      "label": "14.3. Object Detection and Bounding Boxes",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/anchor.html",
      "label": "14.4. Anchor Boxes",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/multiscale-object-detection.html",
      "label": "14.5. Multiscale Object Detection",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/object-detection-dataset.html",
      "label": "14.6. The Object Detection Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/ssd.html",
      "label": "14.7. Single Shot Multibox Detection",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/rcnn.html",
      "label": "14.8. Region-based CNNs (R-CNNs)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/semantic-segmentation-and-dataset.html",
      "label": "14.9. Semantic Segmentation and the Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/transposed-conv.html",
      "label": "14.10. Transposed Convolution",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/fcn.html",
      "label": "14.11. Fully Convolutional Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/neural-style.html",
      "label": "14.12. Neural Style Transfer",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/kaggle-cifar10.html",
      "label": "14.13. Image Classification (CIFAR-10) on Kaggle",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_computer-vision/kaggle-dog.html",
      "label": "14.14. Dog Breed Identification (ImageNet Dogs) on Kaggle",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/index.html",
      "label": "15. Natural Language Processing: Pretraining",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/word2vec.html",
      "label": "15.1. Word Embedding (word2vec)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/approx-training.html",
      "label": "15.2. Approximate Training",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/word-embedding-dataset.html",
      "label": "15.3. The Dataset for Pretraining Word Embeddings",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/word2vec-pretraining.html",
      "label": "15.4. Pretraining word2vec",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/glove.html",
      "label": "15.5. Word Embedding with Global Vectors (GloVe)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/subword-embedding.html",
      "label": "15.6. Subword Embedding",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/similarity-analogy.html",
      "label": "15.7. Word Similarity and Analogy",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/bert.html",
      "label": "15.8. Bidirectional Encoder Representations from Transformers (BERT)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/bert-dataset.html",
      "label": "15.9. The Dataset for Pretraining BERT",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-pretraining/bert-pretraining.html",
      "label": "15.10. Pretraining BERT",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/index.html",
      "label": "16. Natural Language Processing: Applications",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/sentiment-analysis-and-dataset.html",
      "label": "16.1. Sentiment Analysis and the Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/sentiment-analysis-rnn.html",
      "label": "16.2. Sentiment Analysis: Using Recurrent Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/sentiment-analysis-cnn.html",
      "label": "16.3. Sentiment Analysis: Using Convolutional Neural Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/natural-language-inference-and-dataset.html",
      "label": "16.4. Natural Language Inference and the Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/natural-language-inference-attention.html",
      "label": "16.5. Natural Language Inference: Using Attention",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/finetuning-bert.html",
      "label": "16.6. Fine-Tuning BERT for Sequence-Level and Token-Level Applications",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_natural-language-processing-applications/natural-language-inference-bert.html",
      "label": "16.7. Natural Language Inference: Fine-Tuning BERT",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_reinforcement-learning/mdp.html",
      "label": "17.1. Markov Decision Process (MDP)",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_reinforcement-learning/value-iter.html",
      "label": "17.2. Value Iteration",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_reinforcement-learning/qlearning.html",
      "label": "17.3. Q-Learning",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_gaussian-processes/gp-intro.html",
      "label": "18.1. Introduction to Gaussian Processes",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_gaussian-processes/gp-priors.html",
      "label": "18.2. Gaussian Process Priors",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_gaussian-processes/gp-inference.html",
      "label": "18.3. Gaussian Process Inference",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_hyperparameter-optimization/hyperopt-intro.html",
      "label": "19.1. What Is Hyperparameter Optimization?",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_hyperparameter-optimization/hyperopt-api.html",
      "label": "19.2. Hyperparameter Optimization API",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_hyperparameter-optimization/rs-async.html",
      "label": "19.3. Asynchronous Random Search",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_hyperparameter-optimization/sh-intro.html",
      "label": "19.4. Multi-Fidelity Hyperparameter Optimization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_hyperparameter-optimization/sh-async.html",
      "label": "19.5. Asynchronous Successive Halving",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_generative-adversarial-networks/index.html",
      "label": "20. Generative Adversarial Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_generative-adversarial-networks/gan.html",
      "label": "20.1. Generative Adversarial Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_generative-adversarial-networks/dcgan.html",
      "label": "20.2. Deep Convolutional Generative Adversarial Networks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/recsys-intro.html",
      "label": "21.1. Overview of Recommender Systems",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/movielens.html",
      "label": "21.2. The MovieLens Dataset",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/mf.html",
      "label": "21.3. Matrix Factorization",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/autorec.html",
      "label": "21.4. AutoRec: Rating Prediction with Autoencoders",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/ranking.html",
      "label": "21.5. Personalized Ranking for Recommender Systems",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/neumf.html",
      "label": "21.6. Neural Collaborative Filtering for Personalized Ranking",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/seqrec.html",
      "label": "21.7. Sequence-Aware Recommender Systems",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/ctr.html",
      "label": "21.8. Feature-Rich Recommender Systems",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/fm.html",
      "label": "21.9. Factorization Machines",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_recommender-systems/deepfm.html",
      "label": "21.10. Deep Factorization Machines",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/geometry-linear-algebraic-ops.html",
      "label": "22.1. Geometry and Linear Algebraic Operations",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/eigendecomposition.html",
      "label": "22.2. Eigendecompositions",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/single-variable-calculus.html",
      "label": "22.3. Single Variable Calculus",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/multivariable-calculus.html",
      "label": "22.4. Multivariable Calculus",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/integral-calculus.html",
      "label": "22.5. Integral Calculus",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/random-variables.html",
      "label": "22.6. Random Variables",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/maximum-likelihood.html",
      "label": "22.7. Maximum Likelihood",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/distributions.html",
      "label": "22.8. Distributions",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/naive-bayes.html",
      "label": "22.9. Naive Bayes",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/statistics.html",
      "label": "22.10. Statistics",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-mathematics-for-deep-learning/information-theory.html",
      "label": "22.11. Information Theory",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/index.html",
      "label": "23. Appendix: Tools for Deep Learning",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/jupyter.html",
      "label": "23.1. Using Jupyter Notebooks",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/aws.html",
      "label": "23.3. Using AWS EC2 Instances",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/selecting-servers-gpus.html",
      "label": "23.5. Selecting Servers and GPUs",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/contributing.html",
      "label": "23.6. Contributing to This Book",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/utils.html",
      "label": "23.7. Utility Functions and Classes",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_appendix-tools-for-deep-learning/d2l.html",
      "label": "23.8. The d2l API Document",
      "type": "a"
    },
    {
      "href": "https://www.d2l.ai/chapter_references/zreferences.html",
      "label": "References",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:53:52Z",
  "source_url": "https://www.d2l.ai/",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 21822,
  "expected_body_images": 36,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/db16d08cbae0/pages/source.html",
  "local_html": "attachments/db16d08cbae0/pages/article.html",
  "body_base_path": "attachments/db16d08cbae0/pages/",
  "body_markdown_path": "attachments/db16d08cbae0/pages/article.md"
}