{ "source_file": "0930", "source_platform": "Hashnode", "author": "Muhammad Fahad Bashir", "title_listed": "3. Introduction to Neural Networks", "keywords": "", "domain": "机器学习", "content_type": "深度技术解析", "is_paid_flag": "否", "url": "https://mfahadbashir.hashnode.dev/3-introduction-to-neural-networks", "publish_date": "2025-03-28", "corpus_stage": "", "notes": "", "id": "29c6a7b51be5", "collected_at": "2026-10-02T14:10:57", "title": "3. Introduction to Neural Networks", "body_markdown": "3. Introduction to Neural Networks\nUpdated\nMarch 28, 2025\n•\n4\nmin read\n•\nView as Markdown\nM\nMuhammad Fahad Bashir\nMachine Learning, Artificial Intelligence\nPart of series\nDeep Learning Essentials\nThis is the forth article of our series,\nDeep Learning Essentials.\nNeural networks can seem complex, but they are based on simple ideas. In this guide, we will explore what a neural network is and how it works. We'll use an example to make it easier to understand: predicting house prices.\nPredicting House Prices with Machine Learning\nImagine you want to guess the price of a house based on its size. You can use a simple tool from machine learning called\nlinear regression\n.\nLet's say you have data on four houses. You know the size (in square feet) and the price of each house. If you plot this data on a graph, you might see a pattern. You can draw a line through the points on the graph to represent the relationship between size and price.\nThis line is a\nmodel\nthat can predict house prices. If you know the size of a new house, you can use the line to estimate its price.\nThis model is like a\nfunction\n. It takes the house size as input and gives you the price as output.\nThe Simple Neuron\nNow, let's think about this function in a different way. Imagine a circle that does all the calculations. This circle takes the house size and gives you the predicted price. This circle is like a simple\nneuron\n.\nA neuron is like a function. It takes a value as input and gives you a predicted value as output.\nUsing More Features to Predict House Prices\nWhat if you have more information about the house? For example, you might know the number of bedrooms and the postal code.\nThe\nsize\nof the house and the number of\nbedrooms\ncan tell you how big a family the house can support.\nThe\npostal code\ncan tell you the location of the house. Houses in good locations are usually more expensive.\nThe\nnumber of stores\nnearby can tell you how easy it is to shop for things.\nThese pieces of information are called\nfeatures\n.\nThe postal code and the number of stores can tell you how easy it is to live in that location. This can also affect the price of the house.\nYou can combine these features and pass them to another function. This function can then give you the price of the house. These functions are like different neurons.\nThe first neurons take simple features. Then, other neurons use those features to find more complex features.\nThe Magic of Neural Networks\nWe want the AI to find the important features on its own. We want it to predict house prices well without us telling it exactly what to look for.\nThe magic of neural networks is that they can take simple features and find complex features on their own. They use these features to make better predictions.\nFrom One Neuron to a Neural Network\nWe started with one neuron that used size to predict price. Then, we added more neurons and arranged them in layers. This is how we create a more complex model.\nYou can start with one neuron and build a neural network. You can stack neurons in different layers. This creates\ndeep neural networks\n.\nThe first layer is the\ninput layer\n.\nThe layers in the middle are the\nhidden layers\n.\nThe last layer is the\noutput layer\n.\nA neuron is a simple function. You can arrange neurons to make more complex models.\nFully Connected Neural Networks\nA fully connected neural network is one where all the inputs are connected to all the neurons in the next layer.\nLet's look at some important parts of a standard neural network:\nInputs (X)\n: These are the features you use to predict the price, like size and number of bedrooms. Each input goes to all the neurons in the next layer.\nNeurons\n: These are the individual functions that find complex features. The neural network decides what numbers are needed to predict the price well.\nOutput (Ŷ)\n: This is the model's estimate of the price. We use \"Ŷ\" to show that this is the predicted price.\nThere is a difference between the predicted price and the actual price:\nŶ (Y-hat)\nis the model's predicted price.\nY\nis the actual price of the house.\nThis helps us understand how a neural network works. It shows how the network combines simple inputs to find complex features and calculate the output.\nReady to Learn More?\nNeural networks use simple inputs and combine them to find more complex features, like estimating the price of a house.\nAre you interested in building your own neural network? Follow us along the journey to\nlearn the skills you need\n!\nI hope this guide helped you understand the basic ideas behind neural networks. In the next step, you can learn more about each part of the neural network.Follow us\nDeep Learning Essentials\n#\nawfera\n#\ndeep-learning\n#\nneural-network\n#\nintroduction\n#\ntutorial\n#\nconcepts\n17\nviews", "metadata": { "title": "3. Introduction to Neural Networks", "description": "Learn neural networks fundamentals through house price prediction, covering neurons, features, and deep networks in this simple guide", "keywords": null, "author": null, "og:title": "3. Introduction to Neural Networks", "og:description": "Learn neural networks fundamentals through house price prediction, covering neurons, features, and deep networks in this simple guide", "og:url": "https://mfahadbashir.hashnode.dev/3-introduction-to-neural-networks", "og:site_name": "Muhammad Fahad Bashir", "og:image": "https://cdn.hashnode.com/res/hashnode/image/upload/v1743172557114/bca81ec9-a906-444e-9884-611be9277c32.png", "og:image:width": "1200", "og:image:height": "630", "og:type": "article", "twitter:card": "summary_large_image", "twitter:title": "3. Introduction to Neural Networks", "twitter:description": "Learn neural networks fundamentals through house price prediction, covering neurons, features, and deep networks in this simple guide", "twitter:image": "https://cdn.hashnode.com/res/hashnode/image/upload/v1743172557114/bca81ec9-a906-444e-9884-611be9277c32.png", "article:published_time": "2025-03-28T14:36:53.912Z", "article:modified_time": "2025-03-28T14:38:03.089Z", "article:author": "https://mfahadbashir.hashnode.dev/@mfahadbashir" }, "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": [], "images": [ { "status": "ok", "url": "https://cdn.hashnode.com/res/hashnode/image/upload/v1743172557114/bca81ec9-a906-444e-9884-611be9277c32.png", "bytes": 889522, "reused": true, "local_path": "attachments/29c6a7b51be5/images/000.png", "src": "https://cdn.hashnode.com/res/hashnode/image/upload/v1743172557114/bca81ec9-a906-444e-9884-611be9277c32.png", "alt": "3. Introduction to Neural Networks", "downloaded": true }, { "status": "ok", "url": "https://blogger.googleusercontent.com/img/a/AVvXsEhfXXFm3gA8uHn2Ua1OFNU9U6nQqcVFlVEVjFafF1p1vsdjkz3dp8wzDhrqa3LB3QU3uOZC727O3o_WHU73d9960c5U9mKQaQhQVOsvLp3Mgan6FeCr0W_mhalpnSE_x5hJ1GsXX8r-8mIO2tPJEmmwPwFCcVkBZhEMQPw3IGiJ3EuSIZDKKewG-upm30s=w400-h243", "bytes": 41160, "reused": true, "local_path": "attachments/29c6a7b51be5/images/002.jpg", "src": "https://blogger.googleusercontent.com/img/a/AVvXsEhfXXFm3gA8uHn2Ua1OFNU9U6nQqcVFlVEVjFafF1p1vsdjkz3dp8wzDhrqa3LB3QU3uOZC727O3o_WHU73d9960c5U9mKQaQhQVOsvLp3Mgan6FeCr0W_mhalpnSE_x5hJ1GsXX8r-8mIO2tPJEmmwPwFCcVkBZhEMQPw3IGiJ3EuSIZDKKewG-upm30s=w400-h243", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://blogger.googleusercontent.com/img/a/AVvXsEgpcFmXiocyTFqYPgxvqzFZqi00wsKnxTzINnSsyI1StPUWZHrJb-xlYa195tUfU-E4R3u0sZ42fdspI58DIWS7SH6SN-H_Nmgv6Pa8Vab5RxitSJC3yydcj10868ZinPyLfgku65QQKT91kfqFLSvI24iFrvOPu_okAqNIXJ5fgs1Zt23mMuf3N5zewBQ=w400-h234", "bytes": 13591, "reused": true, "local_path": "attachments/29c6a7b51be5/images/003.jpg", "src": "https://blogger.googleusercontent.com/img/a/AVvXsEgpcFmXiocyTFqYPgxvqzFZqi00wsKnxTzINnSsyI1StPUWZHrJb-xlYa195tUfU-E4R3u0sZ42fdspI58DIWS7SH6SN-H_Nmgv6Pa8Vab5RxitSJC3yydcj10868ZinPyLfgku65QQKT91kfqFLSvI24iFrvOPu_okAqNIXJ5fgs1Zt23mMuf3N5zewBQ=w400-h234", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://blogger.googleusercontent.com/img/a/AVvXsEgOKuL9pIkYFwPgrmUr_FXf6i8-JYw7c13cvedmnZ3P-ZKrl0jzF5VnxKFRdUQ29knvUHpvT1V9UOBdN4UzYEFVxTU7JFXy4BV7w56ECtx4Vljs8DBA9eJQ6PMT0E9GEXYOdcd6h72pgORuwqJa_8mkIwy_WPGHt90qS9oM3niLvoL17bV0HDWN_Mqv3TU=w400-h253", "bytes": 29643, "reused": true, "local_path": "attachments/29c6a7b51be5/images/004.jpg", "src": "https://blogger.googleusercontent.com/img/a/AVvXsEgOKuL9pIkYFwPgrmUr_FXf6i8-JYw7c13cvedmnZ3P-ZKrl0jzF5VnxKFRdUQ29knvUHpvT1V9UOBdN4UzYEFVxTU7JFXy4BV7w56ECtx4Vljs8DBA9eJQ6PMT0E9GEXYOdcd6h72pgORuwqJa_8mkIwy_WPGHt90qS9oM3niLvoL17bV0HDWN_Mqv3TU=w400-h253", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://pyimagesearch.com/wp-content/uploads/2016/08/simple_neural_network_header.jpg", "bytes": 50671, "reused": true, "local_path": "attachments/29c6a7b51be5/images/005.jpg", "src": "https://pyimagesearch.com/wp-content/uploads/2016/08/simple_neural_network_header.jpg", "alt": "A simple neural network with Python and Keras - PyImageSearch", "downloaded": true } ], "audio": [], "videos": [], "links": [ { "href": "https://mfahadbashir.hashnode.dev/3-introduction-to-neural-networks.md", "label": "View as Markdown", "type": "a" }, { "href": "https://hashnode.com/@mfahadbashir", "label": "M", "type": "a" }, { "href": "https://www.linkedin.com/in/muhammad-fahad-bashir-09568216a/", "label": "", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/series/deep-learning-essentials", "label": "Part of series Deep Learning Essentials", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/tag/awfera", "label": "# awfera", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/tag/deep-learning", "label": "# deep-learning", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/tag/neural-network", "label": "# neural-network", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/tag/introduction", "label": "# introduction", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/tag/tutorial", "label": "# tutorial", "type": "a" }, { "href": "https://mfahadbashir.hashnode.dev/tag/concepts", "label": "# concepts", "type": "a" } ], "retry_at": "2026-10-03T08:08:07", "repair_version": 2, "repaired_at": "2026-10-14T10:50:44Z", "source_url": "https://mfahadbashir.hashnode.dev/3-introduction-to-neural-networks", "papers": [], "actual_video_files": [], "body_chars": 4757, "expected_body_images": 5, "discovery_status": "ok", "delivery_status": "ok", "missing_reason": "", "raw_html": "attachments/29c6a7b51be5/pages/source.html", "local_html": "attachments/29c6a7b51be5/pages/article.html", "body_base_path": "attachments/29c6a7b51be5/pages/", "body_markdown_path": "attachments/29c6a7b51be5/pages/article.md" }