Foundations

Deep Learning

Deep learning is machine learning using multi-layer neural networks, which learn their own features from raw data instead of relying on hand-engineered ones.

Deep learning is the branch of machine learning built on neural networks with many stacked layers ("depth"). Its defining advantage over earlier statistical ML: a deep network learns its own features directly from raw data (pixels, raw text) instead of requiring a person to hand-engineer them first. It became practical around 2012 once large datasets, GPU compute, and training refinements arrived together.

How it works

Depth buys a hierarchy of representations. Early layers of a CNN respond to edges and colour blobs, middle layers to textures and parts, later layers to whole objects — none of which was specified by hand. The same idea holds for text, where lower layers of a transformer track surface syntax and higher layers carry more abstract structure.

The training loop is unchanged from classical ML: forward pass, compute a loss, backpropagate, step the optimizer. What makes depth work in practice is a set of enabling techniques — residual connections, normalization layers, careful initialization, and ReLU-family activations — plus GPUs to make the matrix multiplications fast enough to iterate.

When it breaks

  • Data hunger. Deep models need far more labelled examples than classical methods. On a few thousand rows of tabular data, gradient boosted trees usually win outright.
  • It fails silently. A bug in preprocessing, a mislabelled class, or a too-high learning rate produces a model that trains without error and simply performs worse — there is no stack trace.
  • Shortcut learning. Networks latch onto whatever correlates with the label in your data (watermarks, backgrounds, hospital scanner IDs) and collapse on deployment data that lacks the shortcut.
  • Cost and reproducibility. Nondeterministic GPU kernels, seed sensitivity, and long training runs make results hard to reproduce exactly.

See also: Neural Network, Backpropagation, CNN, Transformer

Learn more: History & Landscape · Wikipedia: Deep learning

Mentioned in

Lessons where this comes up in context.

On this page