Natural Language Processing with PyTorch

Index

Symbols

• 1x1 convolutions, Network-in-Network Connections (1x1 Convolutions)
• @handles, Corpora, Tokens, and Types
• ^ (hat) notation, The Supervised Learning Paradigm
• _ (underscore), Creating Tensors
• __getitem__ method, Understanding PyTorch’s Dataset Representation, The Surnames Dataset
• __len__ method, Understanding PyTorch’s Dataset Representation, The Surnames Dataset

A

• accuracy, definition of, Correctly Measuring Model Performance: Evaluation Metrics
• activation functions
  • definition of, Activation Functions
  • in perceptrons, The Perceptron: The Simplest Neural Network
  • ReLU, ReLU, Implementing MLPs in PyTorch
  • sigmoid, Sigmoid
  • softmax, Softmax, Implementing MLPs in PyTorch, The SurnameClassifier Model
  • tanh, Tanh
• Adagrad, Choosing an optimizer
• Adam optimizer, Choosing an optimizer, Setting the stage for the training to begin, Tips and Tricks for Training Sequence Models
• adaptive optimizers, Choosing an optimizer
• .add() function, Tensor Operations
• add_token, Vocabulary, The Vocabulary class
• advanced sequence modeling
  • attention mechanism, Capturing More from a Sequence: Attention-Attention in Deep Neural Networks
  • bidirectional recurrent models, Capturing More from a Sequence: Bidirectional Recurrent Models
  • conditioned generation models, Sequence-to-Sequence Models, Encoder–Decoder Models, and Conditioned Generation
  • evaluating sequence generation models, Evaluating Sequence Generation Models
  • neural machine translation example, Example: Neural Machine Translation-The Training Routine and Results
  • sequence-to-sequence ...