Deep Learning with JavaScript Neural networks in TensorFlow.js 1st Edition by Shanqing Cai,Eric Nielsen,Stanley Bileschi 1617296171 9781617296178

Part 1. Motivation and basic concepts

Chapter 1. Deep learning and JavaScript

1.1. Artificial intelligence, machine learning, neural networks, and deep learning

1.2. Why combine JavaScript and machine learning?

1.3. Why TensorFlow.js?

Exercises

Summary

Part 2. A gentle introduction to TensorFlow.js

Chapter 2. Getting started: Simple linear regression in TensorFlow.js

2.1. Example 1: Predicting the duration of a download using TensorFlow.js

2.2. Inside Model.fit(): Dissecting gradient descent from example 1

2.3. Linear regression with multiple input features

2.4. How to interpret your model

Exercises

Summary

Chapter 3. Adding nonlinearity: Beyond weighted sums

3.1. Nonlinearity: What it is and what it is good for

3.2. Nonlinearity at output: Models for classification

3.3. Multiclass classification

Exercises

Summary

Chapter 4. Recognizing images and sounds using convnets

4.1. From vectors to tensors: Representing images

4.2. Your first convnet

4.3. Beyond browsers: Training models faster using Node.js

4.4. Spoken-word recognition: Applying convnets on audio data

Exercises

Summary

Chapter 5. Transfer learning: Reusing pretrained neural networks

5.1. Introduction to transfer learning: Reusing pretrained models

5.2. Object detection through transfer learning on a convnet

Exercises

Summary

Part 3. Advanced deep learning with TensorFlow.js

Chapter 6. Working with data

6.1. Using tf.data to manage data

6.2. Training models with model.fitDataset

6.3. Common patterns for accessing data

6.4. Your data is likely flawed: Dealing with problems in your data

6.5. Data augmentation

Exercises

Summary

Chapter 7. Visualizing data and models

7.1. Data visualization

7.2. Visualizing models after training

Materials for further reading and exploration

Exercises

Summary

Chapter 8. Underfitting, overfitting, and the universal workflow of machine learning

8.1. Formulation of the temperature-prediction problem

8.2. Underfitting, overfitting, and countermeasures

8.3. The universal workflow of machine learning

Exercises

Summary

Chapter 9. Deep learning for sequences and text

9.1. Second attempt at weather prediction: Introducing RNNs

9.2. Building deep-learning models for text

9.3. Sequence-to-sequence tasks with attention mechanism

Materials for further reading

Exercises

Summary

Chapter 10. Generative deep learning

10.1. Generating text with LSTM

10.2. Variational autoencoders: Finding an efficient and structured vec- ctor representation of images

10.3. Image generation with GANs

Materials for further reading

Exercises

Summary

Chapter 11. Basics of deep reinforcement learning

11.1. The formulation of reinforcement-learning problems

11.2. Policy networks and policy gradients: The cart-pole example

11.3. Value networks and Q-learning: The snake game example

Materials for further reading

Exercises

Summary

Part 4. Summary and closing words

Chapter 12. Testing, optimizing, and deploying models

12.1. Testing TensorFlow.js models

12.2. Model optimization

12.3. Deploying TensorFlow.js models on various platforms and environments

Materials for further reading

Exercises

Summary

Chapter 13. Summary, conclusions, and beyond

13.1. Key concepts in review

13.2. Quick overview of the deep-learning workflow and algorithms in TensorFlow.js

13.3. Trends in deep learning

13.4. Pointers for further exploration

Final words

Appendix A. Installing tfjs-node-gpu and its dependencies

A.1. Installing tfjs-node-gpu on Linux

A.2. Installing tfjs-node-gpu on Windows

Appendix B. A quick tutorial of tensors and operations in TensorFlow.js

B.1. Tensor creation and tensor axis conventions

B.2. Basic tensor operations

B.3. Memory management in TensorFlow.js: tf.dispose() and tf.tidy()

B.4. Calculating gradients