Landmark 2 stops to get here · leads to 5

Deep Learning

A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

Your route here

2 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  3. Deep Learning · you are here ✓ understood

Picture it

  1. Prediction The output label
  2. Whole objects Faces, cars
  3. Parts Eyes, wheels, windows
  4. Textures and corners
  5. Edges Early layers
  6. Raw pixels The input
Reading upward, each layer builds more abstract features from the one below, learned from data rather than hand-made.

Deep learning revolutionized AI by enabling machines to automatically learn features from raw data. Unlike traditional machine learning, deep learning models can discover intricate patterns in large datasets without manual feature engineering.

Why “Deep”?

The term refers to the multiple layers (depth) in neural networks. Each layer learns progressively more abstract representations, from simple edges in images to complex concepts.

Breakthroughs

Deep learning enabled major advances in computer vision (ImageNet), natural language processing (GPT, BERT), speech recognition, game playing (AlphaGo), and generative AI.

Where it sits

Before this

Neural Network
Deep Learning

Leads to

Computer Vision Representation Learning AlphaFold Drug Discovery Protein Folding

Explore nearby

Neural Networks Convolutional Neural Network A neural network that scans images with small learned filters, reusing the same weights at every position to build up from edges to whole objects. Neural Networks Recurrent Neural Network A neural network architecture with loops that allow information to persist, designed for sequential data like text and time series. Language & LLMs Transformer A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model. Training Backpropagation The algorithm for computing gradients of the loss with respect to network weights, enabling training through gradient descent. Neural Networks Representation Learning Learning useful features or representations of data automatically, rather than hand-crafting them.