Deep Learning Papers

Concepts

7 concepts

  • Convolutional Neural Networks

    Layered convolutional filters that learn spatial feature hierarchies — the backbone of modern computer vision.

  • Sequence-to-Sequence Learning

    Mapping one variable-length sequence to another with an encoder–decoder, the framing behind neural translation and beyond.

  • Pretraining & Transfer Learning

    Training a large model on a broad corpus once, then adapting it to many downstream tasks — the paradigm behind BERT and GPT.

  • Generative Models

    Learning to generate data — images, text, audio — by modeling its distribution, often through an adversarial game.

  • Attention Mechanism

    Letting a model weight over all positions of its input, so it can focus on the relevant parts rather than a fixed-size summary.

  • Transformers

    An architecture built entirely from attention and feed-forward layers, dispensing with recurrence — now the default for language and much else.

  • Optimization

    The algorithms that actually move the weights: adaptive step sizes, momentum, and the tricks that make deep training converge.