Osoby które kupowały "Natural Language Processing with PyTorch. Build Intelligent Language Applications Using Deep Learning", wybierały także:

• Data Science w Pythonie. Kurs video. Przetwarzanie i analiza danych 149,00 zÅ‚, (67,05 zÅ‚ -55%)
• Matematyka w deep learningu. Co musisz wiedzie 89,00 zÅ‚, (44,50 zÅ‚ -50%)
• Dylemat sztucznej inteligencji. 7 zasad odpowiedzialnego tworzenia technologii 54,90 zÅ‚, (27,45 zÅ‚ -50%)
• Eksploracja danych za pomoc 67,00 zÅ‚, (33,50 zÅ‚ -50%)
• Podr 129,00 zÅ‚, (64,50 zÅ‚ -50%)

Spis treści

Natural Language Processing with PyTorch. Build Intelligent Language Applications Using Deep Learning eBook -- spis treści

• Preface
  • Conventions Used in This Book
  • Using Code Examples
  • OReilly Safari
  • How to Contact Us
  • Acknowledments
• 1. Introduction
  • The Supervised Learning Paradigm
  • Observation and Target Encoding
    • One-Hot Representation
    • TF Representation
    • TF-IDF Representation
    • Target Encoding
  • Computational Graphs
  • PyTorch Basics
    • Installing PyTorch
    • Creating Tensors
    • Tensor Types and Size
    • Tensor Operations
    • Indexing, Slicing, and Joining
    • Tensors and Computational Graphs
    • CUDA Tensors
  • Exercises
  • Solutions
  • Summary
  • References
• 2. A Quick Tour of Traditional NLP
  • Corpora, Tokens, and Types
  • Unigrams, Bigrams, Trigrams, , N-grams
  • Lemmas and Stems
  • Categorizing Sentences and Documents
  • Categorizing Words: POS Tagging
  • Categorizing Spans: Chunking and Named Entity Recognition
  • Structure of Sentences
  • Word Senses and Semantics
  • Summary
  • References
• 3. Foundational Components of Neural Networks
  • The Perceptron: The Simplest Neural Network
  • Activation Functions
    • Sigmoid
    • Tanh
    • ReLU
    • Softmax
  • Loss Functions
    • Mean Squared Error Loss
    • Categorical Cross-Entropy Loss
    • Binary Cross-Entropy Loss
  • Diving Deep into Supervised Training
    • Constructing Toy Data
      • Choosing a model
      • Converting the probabilities to discrete classes
      • Choosing a loss function
      • Choosing an optimizer
    • Putting It Together: Gradient-Based Supervised Learning
  • Auxiliary Training Concepts
    • Correctly Measuring Model Performance: Evaluation Metrics
    • Correctly Measuring Model Performance: Splitting the Dataset
    • Knowing When to Stop Training
    • Finding the Right Hyperparameters
    • Regularization
  • Example: Classifying Sentiment of Restaurant Reviews
    • The Yelp Review Dataset
    • Understanding PyTorchs Dataset Representation
    • The Vocabulary, the Vectorizer, and the DataLoader
      • Vocabulary
      • Vectorizer
      • DataLoader
    • A Perceptron Classifier
    • The Training Routine
      • Setting the stage for the training to begin
      • The training loop
    • Evaluation, Inference, and Inspection
      • Evaluating on test data
      • Inference and classifying new data points
      • Inspecting model weights
  • Summary
  • References
• 4. Feed-Forward Networks for Natural Language Processing
  • The Multilayer Perceptron
    • A Simple Example: XOR
    • Implementing MLPs in PyTorch
  • Example: Surname Classification with an MLP
    • The Surnames Dataset
    • Vocabulary, Vectorizer, and DataLoader
      • The Vocabulary class
      • The SurnameVectorizer
    • The SurnameClassifier Model
    • The Training Routine
      • The training loop
    • Model Evaluation and Prediction
      • Evaluating on the test dataset
      • Classifying a new surname
      • Retrieving the top k predictions for a new surname
    • Regularizing MLPs: Weight Regularization and Structural Regularization (or Dropout)
  • Convolutional Neural Networks
    • CNN Hyperparameters
      • Dimension of the convolution operation
      • Channels
      • Kernel size
      • Stride
      • Padding
      • Dilation
    • Implementing CNNs in PyTorch
  • Example: Classifying Surnames by Using a CNN
    • The SurnameDataset Class
    • Vocabulary, Vectorizer, and DataLoader
    • Reimplementing the SurnameClassifier with Convolutional Networks
    • The Training Routine
    • Model Evaluation and Prediction
      • Evaluating on the test dataset
      • Classifying or retrieving top predictions for a new surname
  • Miscellaneous Topics in CNNs
    • Pooling
    • Batch Normalization (BatchNorm)
    • Network-in-Network Connections (1x1 Convolutions)
    • Residual Connections/Residual Block
  • Summary
  • References
• 5. Embedding Words and Types
  • Why Learn Embeddings?
    • Efficiency of Embeddings
    • Approaches to Learning Word Embeddings
    • The Practical Use of Pretrained Word Embeddings
      • Loading embeddings
      • Relationships between word embeddings
  • Example: Learning the Continuous Bag of Words Embeddings
    • The Frankenstein Dataset
    • Vocabulary, Vectorizer, and DataLoader
    • The CBOWClassifier Model
    • The Training Routine
    • Model Evaluation and Prediction
  • Example: Transfer Learning Using Pretrained Embeddings for Document Classification
    • The AG News Dataset
    • Vocabulary, Vectorizer, and DataLoader
    • The NewsClassifier Model
    • The Training Routine
    • Model Evaluation and Prediction
    • Evaluating on the test dataset
      • Predicting the category of novel news headlines
  • Summary
  • References
• 6. Sequence Modeling for Natural Language Processing
  • Introduction to Recurrent Neural Networks
    • Implementing an Elman RNN
  • Example: Classifying Surname Nationality Using a Character RNN
    • The SurnameDataset Class
    • The Vectorization Data Structures
    • The SurnameClassifier Model
    • The Training Routine and Results
  • Summary
  • References
• 7. Intermediate Sequence Modeling for Natural Language Processing
  • The Problem with Vanilla RNNs (or Elman RNNs)
  • Gating as a Solution to a Vanilla RNNs Challenges
  • Example: A Character RNN for Generating Surnames
    • The SurnameDataset Class
    • The Vectorization Data Structures
      • SurnameVectorizer and END-OF-SEQUENCE
    • From the ElmanRNN to the GRU
    • Model 1: The Unconditioned SurnameGenerationModel
    • Model 2: The Conditioned SurnameGenerationModel
    • The Training Routine and Results
  • Tips and Tricks for Training Sequence Models
  • References
• 8. Advanced Sequence Modeling for Natural Language Processing
  • Sequence-to-Sequence Models, EncoderDecoder Models, and Conditioned Generation
  • Capturing More from a Sequence: Bidirectional Recurrent Models
  • Capturing More from a Sequence: Attention
    • Attention in Deep Neural Networks
  • Evaluating Sequence Generation Models
  • Example: Neural Machine Translation
    • The Machine Translation Dataset
    • A Vectorization Pipeline for NMT
    • Encoding and Decoding in the NMT Model
      • A closer look at attention
      • Learning to search and scheduled sampling
    • The Training Routine and Results
  • Summary
  • References
• 9. Classics, Frontiers, and Next Steps
  • What Have We Learned so Far?
  • Timeless Topics in NLP
    • Dialogue and Interactive Systems
    • Discourse
    • Information Extraction and Text Mining
    • Document Analysis and Retrieval
  • Frontiers in NLP
  • Design Patterns for Production NLP Systems
  • Where Next?
  • References
• Index