Deep Learning with Theano电子书

Deep Learning with Theano

Table of Contents

Deep Learning with Theano

Credits

About the Author

Acknowledgments

About the Reviewers

www.PacktPub.com

eBooks, discount offers, and more

Why subscribe?

Customer Feedback

Preface

What this book covers

Why Theano?

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Downloading the example code

Errata

Piracy

Questions

1. Theano Basics

The need for tensors

Installing and loading Theano

Conda package and environment manager

Installing and running Theano on CPU

GPU drivers and libraries

Installing and running Theano on GPU

Tensors

Graphs and symbolic computing

Operations on tensors

Dimension manipulation operators

Elementwise operators

Reduction operators

Linear algebra operators

Memory and variables

Functions and automatic differentiation

Loops in symbolic computing

Configuration, profiling and debugging

Summary

2. Classifying Handwritten Digits with a Feedforward Network

The MNIST dataset

Structure of a training program

Classification loss function

Single-layer linear model

Cost function and errors

Backpropagation and stochastic gradient descent

Multiple layer model

Convolutions and max layers

Training

Dropout

Inference

Optimization and other update rules

Related articles

Summary

3. Encoding Word into Vector

Encoding and embedding

Dataset

Continuous Bag of Words model

Training the model

Visualizing the learned embeddings

Evaluating embeddings – analogical reasoning

Evaluating embeddings – quantitative analysis

Application of word embeddings

Weight tying

Further reading

Summary

4. Generating Text with a Recurrent Neural Net

Need for RNN

A dataset for natural language

Simple recurrent network

LSTM network

Gated recurrent network

Metrics for natural language performance

Training loss comparison

Example of predictions

Applications of RNN

Related articles

Summary

5. Analyzing Sentiment with a Bidirectional LSTM

Installing and configuring Keras

Programming with Keras

SemEval 2013 dataset

Preprocessing text data

Designing the architecture for the model

Vector representations of words

Sentence representation using bi-LSTM

Outputting probabilities with the softmax classifier

Compiling and training the model

Evaluating the model

Saving and loading the model

Running the example

Further reading

Summary

6. Locating with Spatial Transformer Networks

MNIST CNN model with Lasagne

A localization network

Recurrent neural net applied to images

Unsupervised learning with co-localization

Region-based localization networks

Further reading

Summary

7. Classifying Images with Residual Networks

Natural image datasets

Batch normalization

Global average pooling

Residual connections

Stochastic depth

Dense connections

Multi-GPU

Data augmentation

Further reading

Summary

8. Translating and Explaining with Encoding – decoding Networks

Sequence-to-sequence networks for natural language processing

Seq2seq for translation

Seq2seq for chatbots

Improving efficiency of sequence-to-sequence network

Deconvolutions for images

Multimodal deep learning

Further reading

Summary

9. Selecting Relevant Inputs or Memories with the Mechanism of Attention

Differentiable mechanism of attention

Better translations with attention mechanism

Better annotate images with attention mechanism

Store and retrieve information in Neural Turing Machines

Memory networks

Episodic memory with dynamic memory networks

Further reading

Summary

10. Predicting Times Sequences with Advanced RNN

Dropout for RNN

Deep approaches for RNN

Stacked recurrent networks

Deep transition recurrent network

Highway networks design principle

Recurrent Highway Networks

Further reading

Summary

11. Learning from the Environment with Reinforcement

Reinforcement learning tasks

Simulation environments

Q-learning

Deep Q-network

Training stability

Policy gradients with REINFORCE algorithms

Related articles

Summary

12. Learning Features with Unsupervised Generative Networks

Generative models

Restricted Boltzmann Machines

Deep belief bets

Generative adversarial networks

Improve GANs

Semi-supervised learning

Further reading

Summary

13. Extending Deep Learning with Theano

Theano Op in Python for CPU

Theano Op in Python for the GPU

Theano Op in C for CPU

Theano Op in C for GPU

Coalesced transpose via shared memory, NVIDIA parallel for all

Model conversions

The future of artificial intelligence

Further reading

Summary

Index