Deep learning
How neural networks learn, the frameworks that train them and the architectures behind modern AI, in one map.
Overview
Deep learning is the branch of machine learning that uses neural networks with many layers. Each layer transforms its input a little, and stacked together they learn rich representations directly from raw data: pixels, audio, text and tables. Deep learning powers image recognition, speech, language models and generative AI.
A child learns to recognise cats not from a rulebook but from many examples, gradually building up from edges and shapes to whole animals. Deep networks learn in layers in a similar way.
How neural networks learn
A neural network is layers of weighted sums passed through activation functions. Training repeats one loop: make predictions, measure the error, compute how each weight contributed using Backpropagation, and update weights with an optimizer such as those in Optimizers. Careful weight initialization and learning rate schedules decide whether training starts well and settles well. Techniques such as Normalization layers, Dropout, Mixed precision and Gradient checkpointing make training stable and efficient.
Architectures
- Vision: CNN, ResNet, ViT, U-Net
- Sequences: Recurrent neural networks, LSTM, GRU, Mamba
- Transformers: Attention mechanism, Transformers, Mixture of experts
- Generative: Diffusion models, GAN, VAE
- Tables: Tabular foundation models, In-context learning, TabPFN, TabICL, FT-Transformer
- Representations: Word embeddings, Contrastive learning, Self-supervised learning
Making models smaller and faster
Knowledge distillation, Pruning and quantization methods such as GPTQ and AWQ shrink models for deployment.
The full map
Frameworks
Building blocks
Neural network basics
Architectures
Frontier topics
Large tabular foundation models
Related topics
Frequently asked questions
What is the difference between machine learning and deep learning?
Deep learning is a subset of machine learning that uses multi-layer neural networks to learn representations directly from raw data.
Which framework should I learn?
PyTorch is the most widely used today; JAX is strong for large-scale research on TPUs and GPUs.
Summary
Deep learning stacks neural network layers trained by backpropagation. Frameworks such as PyTorch and JAX, building blocks such as attention and normalisation, and architectures from CNNs to transformers form its toolkit.