deep learning

5 articles · All tags

• Recurrent Neural Networks
  Neural networks with internal state that process sequences step by step, used for language modeling, translation, and time series.
• Backpropagation
  The algorithm that computes gradients through deep networks — the workhorse of training neural networks.
• Large Language Models
  Models trained on enormous text corpora that generate and understand language: how they work, what they can and cannot do.
• The Transformer Architecture
  The attention-based architecture behind modern language models: self-attention, positional encoding, and why it replaced recurrence.
• Convolutional Neural Networks
  Networks that learn from images and grids using shared-weight filters: convolution, pooling, and the architectures that won computer vision.