Topic

Deep Learning

Deep learning trains neural networks with many layers, so each layer learns to build on the one before it. It powers image recognition, speech and large language models. The ideas underneath are simpler than the reputation suggests, and you can see them all at work in a network small enough to watch learning one digit at a time.

1 guide on Deep Learning.

Reference Guide · 20 min read

How Neural Networks Work

The canonical 784-16-16-10 MNIST network as an explorable 3D machine: 16 stations across 4 acts, a 16-step guided journey from pixels to the brain question, all 12,960 weight connections really drawn, and a training row where gradient descent is really computed on an illustrative loss terrain, and a Train mode where the network genuinely learns 10,000 real MNIST digits in your browser.

Neural Networks Deep Learning Backpropagation Gradient Descent MNIST 3D Interactive AI Explainer

Keep learning Deep Learning

[Classic] Deep Residual Learning for Image Recognition (Paper Explained) video · Yannic Kilcher
4: Deep Learning for Computer Vision – Transfer Learning and Fine-Tuning; Intro to HuggingFace video · MIT OpenCourseWare
8: Deep Learning for Natural Language – Transformers, Self-Supervised Learning video · MIT OpenCourseWare
AI, Machine Learning, Deep Learning and Generative AI Explained video · IBM Technology
Attention in transformers, step-by-step | Deep Learning Chapter 6 video · 3Blue1Brown
Automatic Curriculum Learning for Deep RL: a Short Survey video · Flowers INRIA
Backpropagation calculus | Deep Learning Chapter 4 video · 3Blue1Brown
Backpropagation, intuitively | Deep Learning Chapter 3 video · 3Blue1Brown

From the AI Roadmap. Every link was checked.

3D Interactive AI Explainer Backpropagation Gradient Descent MNIST Neural Networks

All Guides

Deep Learning

How Neural Networks Work

Keep learning Deep Learning

Related topics