保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

Revisit consent button We value your privacy We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking "Accept All", you consent to our use of cookies. Customise Reject All Accept All Customise Consent Preferences We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below. The cookies that are categorised as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more NecessaryAlways Active Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

Functional Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

Analytics Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

Performance Performance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.

Advertisement Advertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.

Uncategorised Other uncategorised cookies are those that are being analysed and have not been classified into a category as yet. No cookies to display. Reject All Save My Preferences Accept All Toggle SearchToggle Mobile Navigation Publish AI, ML & data-science insights to a global community of data professionals. Sign inSubmit an Article LatestEditor's PicksNewsletterShipAI

Write For TDS LinkedInXToggle Search Artificial Intelligence

Keep the Gradients Flowing

Optimizing Sparse Neural Networks: Understanding Gradient Flow for Faster Training, and Better Performance in Deep Learning Models. Cristian Leo October 9, 202423 min read

Optimizing Sparse Neural Networks: Understanding Gradient Flow for Faster Training, Improved Efficiency, and Better Performance in Deep Learning Models

AI Image generated depicting the gradients flowing in Neural Networks AI Image generated depicting the gradients flowing in Neural Networks In recent years, the AI field has been obsessed with building larger and larger neural networks, believing that more complexity leads to better performance. Indeed, this approach has yielded incredible results, leading to breakthroughs in image recognition, language translation, and countless other areas. But there's a catch. Just like a massive, overly complex machine can be costly to build and maintain, these enormous neural networks require significant computational resources and time to train. They can be slow, demanding a lot of memory and power, making deploying them on devices with limited resources challenging. Plus, they often become prone to "memorizing" the training data rather than truly understanding the underlying patterns, leading to poor performance on unseen data. Sparse neural networks have partly solved the problem above. Think of sparse NNs as a leaner version of classic NNs. They carefully remove unnecessary parts and connections, resulting in a more efficient and leaner model that still maintains its power. They can train faster, require less memory, and are often more robust to noisy data. However, training these sparse networks has been surprisingly difficult. Researchers have struggled to get them to perform as well as their larger, denser counterparts. The paper we'll be exploring today - Keep the gradients flowing: Using gradient flow to study sparse network optimization by Tessera et al. - offers a fresh perspective on this challenge, taking a deep look at how these sparse networks learn and identifying critical aspects that hinder their training. By focusing on the flow of information within the network, represented by something called "gradient flow ," the researchers show what makes training sparse networks difficult and propose new techniques for optimization. Think of it as uncovering the hidden wiring diagrams of the streamlined machine, and understanding how the remaining parts work together. By revealing the intricacies of gradient flow, we can fine-tune the training process and enable these leaner, more efficient neural networks to reach their full potential. Prepare to be amazed as we unpack the secrets of sparse network optimization!

Gradient Flow in Neural Networks

Every neural network, whether it's a giant, complex model or a streamlined, sparse one, learns by adjusting its connections (weights) to better fit the data. This process of learning is guided by the concept of gradient flow. Think of it as a compass that points the network in the right direction to minimize errors and improve accuracy. But what exactly is gradient flow? In essence, it quantifies how much the network's error changes for its weights. The gradients themselves are essentially derivatives of the network's cost (error) function to its weights. The larger the gradient, the steeper the change in error, indicating that a small change in a particular weight will lead to a larger change in the error. This information is then used by the optimizer to update the weights, taking steps in the direction of lower error. Let's clarify this with a simple analogy. Imagine you are hiking down a mountain in the fog. You don't know the exact path to the valley, but you want to reach the lowest point. Gradient flow acts like the slope of the mountain at your current location. If the slope is steep, you know that taking a step in that direction will lead you to a lower altitude quickly. Otherwise, if the slope is gentle, you'll have to take smaller steps. In mathematical terms, the gradient flow (g_{fp}) at a particular point can be represented using the following formula: Gradient Flow at a particular point - Image by Author Gradient Flow at a particular point - Image by Author where:

So, the gradient flow gives us a sense of the strength of the gradient, indicating the potential for significant change in error to the weights. Larger gradient flows generally imply larger potential changes in error for changes in weights, which can be useful information for the optimizer. However, when it comes to sparse neural networks, this standard formula for gradient flow can be a bit misleading. This is because the standard gradient flow measure includes the gradients of all weights, even those that have been masked (set to zero) during training. These masked weights don't participate in the forward pass or the actual computation of the network, so their gradients don't provide useful information. Including them in the calculation can obscure the true picture of how information flows through the active connections in the sparse network. The researchers addressed this issue with a new metric called Effective Gradient Flow (EGF) , which provides a more insightful and accurate representation of gradient flow within sparse networks. This metric is central to the paper's findings and its contribution to understanding and optimizing sparse networks.

Effective Gradient Flow (EGF)

EGF is designed to provide a more accurate reflection of how information flows through the active connections in sparse networks. It achieves this by focusing solely on the gradients of the non-zero weights. It's like focusing the compass on the relevant parts of the mountain, ignoring the areas that are not part of the path you are currently following. First, we calculate the masked gradient vector (g) for each layer: Masked gradient vector Formula - Image by Author Masked gradient vector Formula - Image by Author where:

Then, the EGF is calculated as the average masked gradient norm across all layers: EGF Formula - Image by Author EGF Formula - Image by Author where:

Essentially, EGF takes the average magnitude of the gradients of active weights across all layers. This provides a much more meaningful representation of the flow of information within the active connections of a sparse network.

Benefits of EGF

EGF offers several significant advantages over the standard gradient flow measure, particularly in the context of sparse networks:

  1. Focuses on Active Connections: By incorporating the binary mask (m_l), EGF ensures that only the gradients of active weights are considered. This directly addresses the issue of misleading gradients from masked weights in standard gradient flow.
  2. Even Distribution Across Layers: EGF computes the average gradient norm across layers, preventing layers with a larger number of weights from disproportionately influencing the overall measure. This ensures that gradient flow is evaluated fairly across all layers, providing a more balanced view of the network's training dynamics.
  3. Stronger Correlation with Performance: The researchers empirically demonstrate that EGF consistently has a higher correlation with performance metrics like accuracy and loss, compared to standard gradient flow measures when used with sparse networks. This implies that EGF is a more reliable indicator of how well a sparse network is learning.

By providing a more accurate and insightful view of gradient flow, EGF helps us better understand the training dynamics of sparse networks. It allows us to pinpoint areas where the flow of information might be hindered and ultimately leads to a better understanding of how to optimize these lean and efficient models.

Same Capacity Sparse vs. Dense Comparison (SC-SDC)

SameCapacity Sparse vs Dense Comparison SC-SDC - Image extracted from the original research paper arXiv:2102.01670 SameCapacity Sparse vs Dense Comparison (SC-SDC) - Image extracted from the original research paper (arXiv:2102.01670) When evaluating the performance of sparse networks, it's crucial to compare them to their dense counterparts in a way that isolates the impact of sparsity. This is where the Same Capacity Sparse vs. Dense Comparison (SC-SDC) framework comes into play. Traditional approaches to comparing sparse and dense networks often involve contrasting a sparse network with fewer parameters with a dense network with a larger number of parameters. While this might seem intuitive, it can lead to biased results. It's like comparing a small, efficient car to a large, luxurious SUV and concluding that the SUV is better simply because it has more features and a larger engine. The difference in performance might be due to the size difference, not necessarily the fundamental characteristics of the two types of vehicles. SC-SDC tackles this issue by ensuring a truly fair comparison. It focuses on comparing sparse and dense networks with the same number of active connections and the same depth (number of layers). This ensures that any performance difference observed can be attributed directly to the presence or absence of connections, rather than differences in overall model capacity. For each layer of the dense network, the corresponding layer in the sparse network is designed to have the same number of active weights. This means that the sparse network may have a larger total number of weights but only a subset of them are active during the training process. Both the sparse and dense networks have the same number of layers (depth). This ensures that the fundamental structure and information processing pathways are similar between the two networks. The active weights in both the sparse and dense networks are initialized using the same distribution. This guarantees that any performance differences are not simply due to differences in initial conditions. To achieve the same capacity, the researchers in the paper use a process of masking. They randomly select a subset of weights to be active (non-zero) in the sparse network, ensuring that the number of active weights in each layer of the sparse network matches the number of weights in the corresponding layer of the dense network.

Benefits of SC-SDC

SC-SDC provides a powerful tool for understanding the optimization dynamics of sparse networks. Creating a level playing field, allows researchers to isolate the effects of sparsity and examine how different optimization and regularization strategies impact performance.

How Architectural Choices and Training Strategies Impact Sparse Networks

The authors explored a wide range of architectural and training choices, including different activation functions, regularization techniques, and optimizers. Let's explore some of their key findings:

Batch Normalization

Batch Normalization (BatchNorm) is a technique designed to improve the training of deep neural networks by normalizing the inputs to each layer. This helps to mitigate issues like internal covariate shift - the change in the distribution of network activations due to the updating of parameters during training - which can slow down learning and make optimization more difficult. Consider a mini-batch of activations from a particular layer, denoted as x1,x2,...,xm, where m is the number of samples in the mini-batch. BatchNorm normalizes these activations using the following steps: Compute the Mini-Batch Mean The mean μB​ of the mini-batch activations is calculated as: Mini-Batch mean Formula - Image by Author Mini-Batch mean Formula - Image by Author This equation sums all the activations in the mini-batch and divides them by the number of activations to find their average value. Computing the mean centers the data around zero, which is essential for normalization. Compute the Mini-Batch Variance The variance σ_B² measures how much the activations vary around the mean: Mini-Batch Variance Formula - Image by Author Mini-Batch Variance Formula - Image by Author For each activation x_i , we subtract the mean μB ​ to find its deviation from the mean, square this deviation to ensure it's positive, and then average these squared deviations over all activations. The variance quantifies the spread or dispersion of the activations. Normalize the Activations Each activation x_i ​ is then normalized to produce x^i​ : Activation Normalization Formula - Image by Author Activation Normalization Formula - Image by Author In this equation, ϵ is a small constant (like 10^{-5}) added to the variance to prevent division by zero and improve numerical stability. By subtracting the mean and dividing by the standard deviation (the square root of the variance), we transform the activations to have a mean of zero and a variance of one. This standardization ensures that the scale of the activations remains consistent across layers and during training. Scale and Shift Finally, we apply a linear transformation to the normalized activations: Scale and Shift Formula - Image by Author Scale and Shift Formula - Image by Author Here, γ and β are learnable parameters that allow the network to restore the original distribution of activations if necessary. γ scales the normalized activation, and β shifts it. This step provides the network with the flexibility to adjust the normalized activations, which can improve its representational capacity. In the context of sparse networks - networks where many weights are set to zero, reducing the number of active connections - BatchNorm is particularly beneficial:

The Sensitivity of EWMA Optimizers to High Gradient Flow

The paper investigates how different optimizers perform in the context of sparse networks, focusing on those that use an Exponentially Weighted Moving Average (EWMA) of past gradients, such as Adam and RMSProp. These optimizers adapt the learning rates based on the historical behavior of gradients, which can make them sensitive to high gradient flows. Let's delve deeper into how these optimizers work, using the Adam optimizer as an example.

Adam Optimizer

Compute Gradients At each time step t , we compute the gradients of the loss function L_t ​ for the parameters θ : Gradients Formula - Image by Author Gradients Formula - Image by Author Here, ∇θLt(θt−1) represents the vector of partial derivatives of the loss to each parameter in θ , evaluated at the previous parameter values θt−1​. Update Biased First Moment Estimate ( m_t ) The first-moment estimate mtm_tmt​ is an EWMA of the gradients: First moment Estimate Formula - Image by Author First moment Estimate Formula - Image by Author

Update Biased Second Moment Estimate ( v_t ) The second-moment estimate v_t ​ is an EWMA of the squared gradients: Second Moment Estimate - Image by Author Second Moment Estimate - Image by Author Here:

Compute Bias-Corrected Estimates Since mtm_tmt​ and v_t ​ are initialized at zero, they are biased towards zero, especially in the initial time steps. To correct this bias, we compute: Bias-Corrected Estimates - Image by Author Bias-Corrected Estimates - Image by Author The terms 1−β1 ​ and 1−β2 adjust the estimates based on how many time steps have occurred. As t increases, β1​ and β2 ​ approach zero, reducing the bias in m_t and v_t. Update Parameters Finally, we update the parameters θ : Parameters Update - Image by Author Parameters Update - Image by Author Here:

When gradients are large (high gradient flow), EWMA optimizers can exhibit instability due to:

L2 Regularization

L2 Regularization (also known as weight decay) adds a penalty to the loss function proportional to the square of the magnitude of the weights: L2 Regularization - Image by Author L2 Regularization - Image by Author Here:

The gradient of the regularized loss for θ is: Gradient with L2 Regularization - Image by Author Gradient with L2 Regularization - Image by Author The term λθ increases the magnitude of the gradients, potentially leading to higher gradient flows. In sparse networks, due to the combination of L2 regularization and fewer active parameters (weights), the gradients can be larger in magnitude. This is because the regularization term λθ adds a component proportional to the weights, and in sparse networks, the remaining weights might carry more significance. Additionally, the sensitivity of EWMA optimizers like Adam and RMSProp to high gradients can cause instability, slow convergence, or even divergence during training. The inflated v_t ​ can lead to excessively small parameter updates, hindering learning. Optimizers that do not rely on EWMA of past gradients, such as Stochastic Gradient Descent (SGD) or Adagrad , may perform better in these situations because they are less sensitive to sudden changes in gradient magnitudes.

The Potential of Non-Sparse Activation Functions

The paper also explored the impact of different activation functions on the performance of sparse networks. Traditionally, ReLU (Rectified Linear Unit) has been a popular choice due to its simplicity and ability to mitigate the vanishing gradient problem. However, the researchers explored other activation functions, such as Swish and PReLU. They discovered that these non-sparse activation functions, which don't inherently produce zero gradients, can be beneficial for sparse networks. This is particularly true for Swish, which has a non-monotonic behavior. Swish allows for the flow of negative gradients, which can contribute to better gradient flow and ultimately enhance the training process.

ReLU (Rectified Linear Unit)

The ReLU activation function is defined as: ReLU Formula - Image by Author ReLU Formula - Image by Author Its derivative, which is essential for backpropagation, is: ReLU Derivative - Image by Author ReLU Derivative - Image by Author For inputs x≤0 , the output is zero, introducing sparsity in the activations. If a neuron gets stuck with negative inputs, it may stop learning because the gradient f′(x) is zero, preventing weight updates. This phenomenon is known as the "dying ReLU" problem.

Swish Activation Function

The Swish activation function is defined as: Swish Formula - Image by Author Swish Formula - Image by Author Where σ(βx) is the sigmoid function: Sigmoid Function Formula - Image by Author Sigmoid Function Formula - Image by Author The derivative of Swish can be derived using the product rule of differentiation: Swish Derivative - Image by Author Swish Derivative - Image by Author The term σ(βx) represents the contribution from the linear part x. The term βx⋅σ(βx)(1−σ(βx)) comes from differentiating the sigmoid function. Swish is not strictly increasing or decreasing, which can help in learning complex patterns. Unlike ReLU, Swish is smooth and differentiable everywhere, which can facilitate optimization. Even for negative x , the gradient f′(x) is non-zero, allowing for continued learning.

PReLU (Parametric ReLU)

PReLU introduces a learnable parameter aaa to control the slope for negative inputs: PReLU Formula - Image by Author PReLU Formula - Image by Author The derivative is: PReLU derivative - Image by Author PReLU derivative - Image by Author The parameter aaa (typically a small positive value) allows the activation function to have a small, non-zero gradient when x <0. This prevents the neuron from dying, as it can still update its weights even when the input is negative. The parameter a is learned during training, allowing the network to adjust the activation function based on the data. With a >0, the gradient for negative inputs is non-zero, preventing neurons from becoming inactive. In sparse networks, using activation functions that allow for non-zero gradients even when the input is negative can be particularly beneficial. Non-sparse activation functions like Swish and PReLU ensures that neurons continue to learn even when they receive negative inputs, due to non-zero gradients. By preventing gradients from becoming zero, these activation functions facilitate better propagation of error signals during backpropagation, enhancing the learning process. Also, neurons are less likely to become inactive permanently, as can happen with ReLU when weights update in such a way that the neuron only receives negative inputs.

Results

The results from these experiments highlight several important points: Gradient flow is a critical factor in the training of sparse networks. Understanding and controlling gradient flow is crucial for achieving good performance. BatchNorm is particularly beneficial for sparse networks, helping to stabilize the training process. EWMA optimizers can be problematic when used with certain regularization techniques or data augmentation strategies. This is due to their sensitivity to high gradient flow. Non-sparse activation functions can improve the performance of sparse networks. This can be attributed to their ability to facilitate a more stable and informative gradient flow.

The Role of Initialization

One of the most important takeaways from this research is that initialization is just one piece of the puzzle when it comes to optimizing sparse networks. Traditionally, a lot of research focused on finding optimal weight initialization strategies for sparse networks. However, the paper reveals that other factors, like optimization algorithms, activation functions, and regularization techniques, play a crucial role in determining the performance of sparse networks. This broader perspective emphasizes the need to reconsider many of the default choices made when training neural networks, especially in the context of sparse networks. We can no longer simply assume that optimization strategies developed for dense networks will be equally effective for sparse networks.

The Importance of Stable Gradient Flow

Understanding gradient flow is essential when training neural networks, especially sparse ones. In simple terms, gradient flow refers to how gradients - the signals used to update the network's weights during training - propagate through the layers of a neural network. The paper emphasizes that achieving a stable and informative gradient flow is crucial for the successful training of sparse networks. When the gradient flow is stable, the network can effectively update its weights, learn from the data, and improve its performance over time. This insight opens up exciting avenues for future research. By focusing on developing new regularization techniques or normalization methods that promote stable gradient flow specifically in sparse networks, we can enhance their learning capabilities. This could involve modifying existing methods or creating entirely new approaches tailored to address the unique challenges posed by sparsity in neural networks. Screenshot of Gradient Flow Visualizer Web App — Built by Author Screenshot of Gradient Flow Visualizer Web App — Built by Author To help you see firsthand how different components affect both the training process and gradient flow in dense and sparse neural networks, I've built a web app, which allows you to train neural networks with configurations that you customize, giving you a hands-on understanding of these concepts. You can specify parameters such as the number of hidden layers in the model and the number of nodes in each hidden layer. The app lets you choose the activation function used after each layer, offering options like ReLU, PReLU, Swish, and Sigmoid. You can set the learning rate, determine how many epochs (iterations) you want the model to train over, and select the batch size for training. Additionally, the app provides datasets from the sci-kit-learn library for you to work with. For regression tasks, you can choose the "Diabetes" dataset, and for classification tasks, options include the "Iris," "Wine," and "Breast Cancer" datasets. There's also the option to apply techniques like gradient clipping and gradient normalization to further experiment with training dynamics. The app is free to use, and the code is available here:

GitHub - cristianleoo/gradient-flow-optimizer-neural-networks You may be able to access the website here: However, streamlit - the hosting platform - may temporarily bring it down. If that happens don't hesitate to reach out to me and I will bring it up again. If you want to self-host it, you can follow the guide in GitHub repo. Now, back to the app. Once you've set up your desired configuration, the app creates both dense and sparse neural network models based on your settings and trains them on the selected dataset. During training, it collects data on gradient flow, loss, and various performance metrics, allowing you to observe how different factors influence the learning process. For example, if you configure a dense neural network with three hidden layers and ten nodes per layer, the app visualizes this architecture for you. Example of a Dense Neural Network architecture with 3 hidden layers and 10 nodes per layer - Image by Author Example of a Dense Neural Network architecture with 3 hidden layers and 10 nodes per layer - Image by Author The app will also generate a train a sparse neural network with the same structural parameters, you'll see how sparsity changes the architecture. These visual representations help you understand the structural differences between dense and sparse networks. Example of a Sparse Neural Network architecture with 3 hidden layers and 10 nodes per layer - Image by Author Example of a Sparse Neural Network architecture with 3 hidden layers and 10 nodes per layer - Image by Author After the training is completed, the app provides a range of visualizations and statistics to help you delve deeper into gradient flow and model performance. For both dense and sparse models, it plots metrics over time, such as loss, accuracy, precision, recall, and F1 score. These graphs enable you to see how the models' performance evolves throughout the training process, giving you insights into their learning behaviors. For instance, you might examine a plot of the Mean Squared Error (MSE) over 20 epochs of training, which illustrates how the error decreases as the model learns. This can show you how quickly the model is converging and whether it's learning effectively from the data. MSE plot for NN training over 20 epochs - Image by Author MSE plot for NN training over 20 epochs - Image by Author The app also provides visualizations of gradient flow distribution, such as boxplots that display the distribution of gradient norms across the different layers of the network. These plots help you identify potential issues like vanishing or exploding gradients by highlighting how the gradients vary throughout the network. By examining these visualizations, you can see whether the gradients are consistently flowing through all layers or if they're diminishing or amplifying in certain parts of the network. Gradient Flow Distribution Across Layers - Image by Author Gradient Flow Distribution Across Layers - Image by Author Additionally, the app plots how the gradient norms for each layer change over time during training. This allows you to observe trends and spot any potential instabilities in the gradient flow as the model learns. For example, you might notice that the gradients in the earlier layers are gradually decreasing, which could indicate the vanishing gradient problem. Alternatively, if the gradients are increasing uncontrollably, it might signal exploding gradients. Gradient Flow Across Layers - Image by Author Gradient Flow Across Layers - Image by Author Moreover, the app provides detailed statistics for each layer, including initial and final gradient values, the mean and standard deviation of the gradients, and percentile information. It also reports the number of vanishing gradients (very small gradients that may hinder learning) and exploding gradients (very large gradients that can cause instability). These statistics give you quantitative measures to assess the health of your network's training process. Stats table for gradients across layers - Image by Author Stats table for gradients across layers - Image by Author Interpreting these results is key to understanding and improving your models. A stable gradient flow is characterized by consistent, non-zero gradient norms across layers and over time. When examining the gradient flow distribution plots, look for relatively uniform distributions, indicating that gradients are properly propagating through the network. In the gradient flow over time plots, smooth and steady lines suggest that the gradients are stable, which is desirable for effective learning. If you observe very small gradient norms, especially in the earlier layers of the network, this could point to the vanishing gradient problem. In this scenario, the gradients are too small to make meaningful updates to the weights, hindering the network's ability to learn from the data. Conversely, extremely large gradient norms might indicate exploding gradients, where the updates become so large that they destabilize the training process. Both situations can be identified through the visualizations and statistics provided by the app. By experimenting with different activation functions, learning rates, and other parameters, you can assess their impact on gradient flow. For instance, you might find that using the Swish activation function leads to a more stable gradient flow compared to ReLU in a sparse network. Comparing the results between dense and sparse networks also helps you understand how sparsity affects the flow of information. You might observe that sparse networks are more susceptible to vanishing gradients, emphasizing the importance of careful configuration and potentially the use of techniques like Batch Normalization or alternative activation functions to mitigate this issue.

Conclusion

The research highlighted the importance of gradient flow, the need for a broader perspective on sparse network optimization, and the potential for tailored optimization strategies. By embracing a more nuanced understanding of gradient flow and carefully considering architectural choices and training strategies, we can better understand what's happening behind this "black-box" architecture. This exploration is just the beginning. As the field of deep learning continues to evolve, the ideas presented in "Keep the Gradients Flowing" will undoubtedly shape the future of sparse network optimization. Master the math I provided in this article, clone the repo from GitHub, make the code your own, and contribute to the research of gradient flow optimization!

References

Register Now to Continue Reading

Unlock Towards Data Science with a Free Account

All articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more. Register for freeSign in to your account

Written By

Cristian Leo

See all from Cristian Leo Artificial IntelligenceData ScienceDeep LearningMachine LearningMathematics Share This Article

Towards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program. Write for TDS

Related Articles

What Makes Bagging Algorithms Superior?

Machine Learning Evidence that proves why bagging algorithms like random forest perform better than decision tree Jason Chong May 2, 20226 min read

Top 3 Python Functions You Don't Know About (Probably)

Artificial Intelligence Cleaner Code and Fewer Loops? Count me in. Dario Radečić March 14, 20204 min read

What is Bias-Variance Tradeoff?

Artificial Intelligence Avoid the mistake of overfitting and underfitting NVS Yashwanth September 21, 20204 min read

Going for Gold: Predicting medal outcomes in the Olympics using Generalized Linear Modeling

Data Science A fun introduction to GLMs using an Olympics dataset Jamshaid Shahir, Ph.D August 6, 202110 min read

BYOL -The Alternative to Contrastive Self-Supervised Learning

Deep Learning Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning by J. Grill et. al. Sascha Kirch September 7, 202310 min read

Managing Machine Learning projects

Deep Learning A journey of tooling decisions Tobias Petri September 28, 202011 min read

3 Different Ways to Tune Hyperparameters (Interactive Python Code)

Artificial Intelligence An Interactive Guide to Optimizing and Tuning Hyperparameters Will Badr August 6, 20195 min read

A Step-by-Step Guide to Completely Learn Data Science by Doing Projects

Artificial Intelligence Build a portfolio and become job-ready as you learn Sharan Kumar Ravindran September 19, 202112 min read

Understand what drives your customer behavior in clicks

Artificial Intelligence Key Driver Analysis with PowerBI Deepak Verma January 10, 20215 min read

Your home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals. Subscribe to Our NewsletterWrite For TDS•About•Advertise•Privacy Policy•Terms of Use © Insight Media Group, LLC 2026•The New Stack•roadmap.sh•Creator Network