Deep Learning | Towards Data Science https://towardsdatascience.com/category/artificial-intelligence/deep-learning/ Publish AI, ML & data-science insights to a global community of data professionals. Fri, 12 Dec 2025 21:56:23 +0000 en-US hourly 1 https://wordpress.org/?v=6.8.3 https://towardsdatascience.com/wp-content/uploads/2025/02/cropped-Favicon-32x32.png Deep Learning | Towards Data Science https://towardsdatascience.com/category/artificial-intelligence/deep-learning/ 32 32 Decentralized Computation: The Hidden Principle Behind Deep Learning https://towardsdatascience.com/the-power-of-decentralization/ Fri, 12 Dec 2025 15:47:00 +0000 https://towardsdatascience.com/?p=607888 Most breakthroughs in deep learning — from simple neural networks to large language models — are built upon a principle that is much older than AI itself: decentralization. Instead of relying on a powerful “central planner” coordinating and commanding the behaviors of other components, modern deep-learning-based AI models succeed because many simple units interact locally […]

The post Decentralized Computation: The Hidden Principle Behind Deep Learning appeared first on Towards Data Science.

]]> Optimizing PyTorch Model Inference on AWS Graviton https://towardsdatascience.com/optimizing-pytorch-model-inference-on-aws-graviton/ Wed, 10 Dec 2025 12:00:00 +0000 https://towardsdatascience.com/?p=607814 Tips for accelerating AI/ML on CPU — Part 2

The post Optimizing PyTorch Model Inference on AWS Graviton appeared first on Towards Data Science.

]]> Optimizing PyTorch Model Inference on CPU https://towardsdatascience.com/optimizing-pytorch-model-inference-on-cpu/ Mon, 08 Dec 2025 12:00:00 +0000 https://towardsdatascience.com/?p=607812 Flyin’ Like a Lion on Intel Xeon

The post Optimizing PyTorch Model Inference on CPU appeared first on Towards Data Science.

]]> On the Challenge of Converting TensorFlow Models to PyTorch https://towardsdatascience.com/on-the-challenge-of-converting-tensorflow-models-to-pytorch/ Fri, 05 Dec 2025 12:30:00 +0000 https://towardsdatascience.com/?p=607800 How to upgrade and optimize legacy AI/ML models

The post On the Challenge of Converting TensorFlow Models to PyTorch appeared first on Towards Data Science.

]]> Do Labels Make AI Blind? Self-Supervision Solves the Age-Old Binding Problem https://towardsdatascience.com/emergent-object-binding-from-self-supervised-not-supervised-learning/ Thu, 04 Dec 2025 17:30:00 +0000 https://towardsdatascience.com/?p=607810 A new NeurIPS 2025 paper shows how self-supervised learning imbues ViT with better image understanding than supervised learning

The post Do Labels Make AI Blind? Self-Supervision Solves the Age-Old Binding Problem appeared first on Towards Data Science.

]]> Overcoming the Hidden Performance Traps of Variable-Shaped Tensors: Efficient Data Sampling in PyTorch https://towardsdatascience.com/overcoming-the-hidden-performance-traps-of-variable-shaped-tensors-efficient-data-sampling-in-pytorch/ Wed, 03 Dec 2025 17:00:00 +0000 https://towardsdatascience.com/?p=607796 PyTorch Model Performance Analysis and Optimization — Part 11

The post Overcoming the Hidden Performance Traps of Variable-Shaped Tensors: Efficient Data Sampling in PyTorch appeared first on Towards Data Science.

]]> Neural Networks Are Blurry, Symbolic Systems Are Fragmented. Sparse Autoencoders Help Us Combine Them. https://towardsdatascience.com/neuro-symbolic-systems-the-art-of-compromise-2/ Thu, 27 Nov 2025 17:24:06 +0000 https://towardsdatascience.com/?p=607756 Neural and symbolic models compress the world in fundamentally different ways, and Sparse Autoencoders (SAEs) offer a bridge to connect them.

The post Neural Networks Are Blurry, Symbolic Systems Are Fragmented. Sparse Autoencoders Help Us Combine Them. appeared first on Towards Data Science.

]]> PyTorch Tutorial for Beginners: Build a Multiple Regression Model from Scratch https://towardsdatascience.com/pytorch-tutorial-for-beginners-build-a-multiple-regression-model-from-scratch/ Wed, 19 Nov 2025 14:00:00 +0000 https://towardsdatascience.com/?p=607678 Hands-on PyTorch: Building a 3-layer neural network for multiple regression

The post PyTorch Tutorial for Beginners: Build a Multiple Regression Model from Scratch appeared first on Towards Data Science.

]]> Understanding Convolutional Neural Networks (CNNs) Through Excel https://towardsdatascience.com/understanding-convolutional-neural-networks-cnns-through-excel/ Mon, 17 Nov 2025 19:54:54 +0000 https://towardsdatascience.com/?p=607662 Deep learning is often seen as a black box. We know that it learns from data, but we rarely stop to ask how it truly learns.
What if we could open that box and watch each step happen right before our eyes?
With Excel, we can do exactly that, see how numbers turn into patterns, and how simple calculations become the foundation of what we call “deep learning.”
In this article, we will build a tiny Convolutional Neural Network (CNN) directly in Excel to understand, step by step, how machines detect shapes, patterns, and meaning in images.

The post Understanding Convolutional Neural Networks (CNNs) Through Excel appeared first on Towards Data Science.

]]> AI Papers to Read in 2025 https://towardsdatascience.com/ai-papers-to-read-in-2025/ Wed, 05 Nov 2025 21:47:58 +0000 https://towardsdatascience.com/?p=607566 And Why They Matter for Anyone Working With AI

The post AI Papers to Read in 2025 appeared first on Towards Data Science.

]]> RF-DETR Under the Hood: The Insights of a Real-Time Transformer Detection https://towardsdatascience.com/rf-detr-under-the-hood-the-insights-of-a-real-time-transformer-detection/ Fri, 31 Oct 2025 12:30:00 +0000 https://towardsdatascience.com/?p=607526 From rigid grids to adaptive attention, this is the evolutionary path that made detection transformers fast, flexible, and formidable.

The post RF-DETR Under the Hood: The Insights of a Real-Time Transformer Detection appeared first on Towards Data Science.

]]> How to Classify Lung Cancer Subtype from DNA Copy Numbers Using PyTorch https://towardsdatascience.com/classification-of-lung-cancer-type-from-genomic-copy-number-profiles-using-a-convolutional-neural-network/ Fri, 17 Oct 2025 17:02:09 +0000 https://towardsdatascience.com/?p=607414 A step-by-step introduction to understanding cancer from the perspective of a data scientist.

The post How to Classify Lung Cancer Subtype from DNA Copy Numbers Using PyTorch appeared first on Towards Data Science.

]]> MobileNetV2 Paper Walkthrough: The Smarter Tiny Giant https://towardsdatascience.com/mobilenetv2-paper-walkthrough-the-smarter-tiny-giant/ Fri, 03 Oct 2025 12:30:00 +0000 https://towardsdatascience.com/?p=607331 Understanding and implementing MobileNetV2 with PyTorch  — the next generation of MobileNetV1

The post MobileNetV2 Paper Walkthrough: The Smarter Tiny Giant appeared first on Towards Data Science.

]]> How to Improve the Efficiency of Your PyTorch Training Loop https://towardsdatascience.com/improve-efficiency-of-your-pytorch-training-loop/ Wed, 01 Oct 2025 19:16:04 +0000 https://towardsdatascience.com/?p=607314 Learn how to diagnose and resolve bottlenecks in PyTorch using the num_workers, pin_memory, and profiler parameters to maximize training performance.

The post How to Improve the Efficiency of Your PyTorch Training Loop appeared first on Towards Data Science.

]]> Learning Triton One Kernel At a Time: Vector Addition https://towardsdatascience.com/learning-triton-one-kernel-at-a-time-vector-addition/ Sat, 27 Sep 2025 16:00:00 +0000 https://towardsdatascience.com/?p=607283 The basics of GPU programming, optimisation, and your first Triton kernel

The post Learning Triton One Kernel At a Time: Vector Addition appeared first on Towards Data Science.

]]> PyTorch Explained: From Automatic Differentiation to Training Custom Neural Networks https://towardsdatascience.com/the-basics-of-deep-learning-with-pytorch-in-1-hour/ Wed, 24 Sep 2025 18:19:59 +0000 https://towardsdatascience.com/?p=607255 Deep learning is shaping our world as we speak. In fact, it has been slowly revolutionizing software since the early 2010s. In 2025, PyTorch is at the forefront of this revolution, emerging as one of the most important libraries to train neural networks. Whether you are working with computer vision, building large language models (LLMs), […]

The post PyTorch Explained: From Automatic Differentiation to Training Custom Neural Networks appeared first on Towards Data Science.

]]> The SyncNet Research Paper, Clearly Explained https://towardsdatascience.com/syncnet-paper-easily-explained/ Sat, 20 Sep 2025 14:00:00 +0000 https://towardsdatascience.com/?p=607194 A Deep Dive into "Out of Time: Automated Lip Sync in the Wild"

The post The SyncNet Research Paper, Clearly Explained appeared first on Towards Data Science.

]]> MobileNetV1 Paper Walkthrough: The Tiny Giant https://towardsdatascience.com/the-tiny-giant-mobilenetv1/ Thu, 04 Sep 2025 17:35:47 +0000 https://towardsdatascience.com/?p=607035 Understanding and implementing MobileNetV1 from scratch with PyTorch

The post MobileNetV1 Paper Walkthrough: The Tiny Giant appeared first on Towards Data Science.

]]> Positional Embeddings in Transformers: A Math Guide to RoPE & ALiBi https://towardsdatascience.com/positional-embeddings-in-transformers-a-math-guide-to-rope-alibi/ Tue, 26 Aug 2025 14:00:00 +0000 https://towardsdatascience.com/?p=606947 Learn APE, RoPE, and ALiBi positional embeddings for GPT — intuitions, math, PyTorch code, and experiments on TinyStories

The post Positional Embeddings in Transformers: A Math Guide to RoPE & ALiBi appeared first on Towards Data Science.

]]> From Genes to Neural Networks: Understanding and Building NEAT (Neuro-Evolution of Augmenting Topologies) from Scratch https://towardsdatascience.com/from-genes-to-neural-networks-understanding-and-building-neat-neuro-evolution-of-augmenting-topologies-from-scratch/ Mon, 11 Aug 2025 18:03:44 +0000 https://towardsdatascience.com/?p=606830 Practical Neuroevolution: Reproducing NEAT’s Innovations and Code Walkthrough

The post From Genes to Neural Networks: Understanding and Building NEAT (Neuro-Evolution of Augmenting Topologies) from Scratch appeared first on Towards Data Science.

]]>