Deep Learning Cookbook

Name: Deep Learning Cookbook | Practical Recipes to Get Started Quickly
Brand: O'Reilly
Price: 36.49 EUR
Availability: OnlineOnly

Practical Recipes to Get Started Quickly

Douwe Osinga(Author)

O'Reilly (Publisher)

Published on 5. June 2018

252 pages

E-Book

PDF with Adobe-DRM

System requirements

978-1-4919-9581-5 (ISBN)

€36.49incl. 7% vat

System requirements

for PDF with Adobe-DRM

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Copyright
Table of Contents
Preface
A Brief History of Deep Learning
Why Now?
What Do You Need to Know?
How This Book Is Structured
Conventions Used in This Book
Accompanying Code
O'Reilly Safari
How to Contact Us
Acknowledgments
Chapter 1. Tools and Techniques
1.1 Types of Neural Networks
Fully Connected Networks
Convolutional Networks
Recurrent Networks
Adversarial Networks and Autoencoders
Conclusion
1.2 Acquiring Data
Wikipedia
Wikidata
OpenStreetMap
Twitter
Project Gutenberg
Flickr
The Internet Archive
Crawling
Other Options
1.3 Preprocessing Data
Getting a Balanced Training Set
Creating Data Batches
Training, Testing, and Validation Data
Preprocessing of Text
Preprocessing of Images
Conclusion
Chapter 2. Getting Unstuck
2.1 Determining That You Are Stuck
Problem
Solution
Discussion
2.2 Solving Runtime Errors
Problem
Solution
Discussion
2.3 Checking Intermediate Results
Problem
Solution
Discussion
2.4 Picking the Right Activation Function (for Your Final Layer)
Problem
Solution
Discussion
2.5 Regularization and Dropout
Problem
Solution
Discussion
2.6 Network Structure, Batch Size, and Learning Rate
Problem
Solution
Discussion
Chapter 3. Calculating Text Similarity Using Word Embeddings
3.1 Using Pretrained Word Embeddings to Find Word Similarity
Problem
Solution
Discussion
3.2 Word2vec Math
Problem
Solution
Discussion
3.3 Visualizing Word Embeddings
Problem
Solution
Discussion
3.4 Finding Entity Classes in Embeddings
Problem
Solution
Discussion
3.5 Calculating Semantic Distances Inside a Class
Problem
Solution
Discussion
3.6 Visualizing Country Data on a Map
Problem
Solution
Discussion
Chapter 4. Building a Recommender System Based on Outgoing Wikipedia Links
4.1 Collecting the Data
Problem
Solution
Discussion
4.2 Training Movie Embeddings
Problem
Solution
Discussion
4.3 Building a Movie Recommender
Problem
Solution
Discussion
4.4 Predicting Simple Movie Properties
Problem
Solution
Discussion
Chapter 5. Generating Text in the Style of an Example Text
5.1 Acquiring the Text of Public Domain Books
Problem
Solution
Discussion
5.2 Generating Shakespeare-Like Texts
Problem
Solution
Discussion
5.3 Writing Code Using RNNs
Problem
Solution
Discussion
5.4 Controlling the Temperature of the Output
Problem
Solution
Discussion
5.5 Visualizing Recurrent Network Activations
Problem
Solution
Discussion
Chapter 6. Question Matching
6.1 Acquiring Data from Stack Exchange
Problem
Solution
Discussion
6.2 Exploring Data Using Pandas
Problem
Solution
Discussion
6.3 Using Keras to Featurize Text
Problem
Solution
Discussion
6.4 Building a Question/Answer Model
Problem
Solution
Discussion
6.5 Training a Model with Pandas
Problem
Solution
6.6 Checking Similarities
Problem
Solution
Discussion
Chapter 7. Suggesting Emojis
7.1 Building a Simple Sentiment Classifier
Problem
Solution
Discussion
7.2 Inspecting a Simple Classifier
Problem
Solution
Discussion
7.3 Using a Convolutional Network for Sentiment Analysis
Problem
Solution
Discussion
7.4 Collecting Twitter Data
Problem
Solution
Discussion
7.5 A Simple Emoji Predictor
Problem
Solution
Discussion
7.6 Dropout and Multiple Windows
Problem
Solution
Discussion
7.7 Building a Word-Level Model
Problem
Solution
Discussion
7.8 Constructing Your Own Embeddings
Problem
Solution
Discussion
7.9 Using a Recurrent Neural Network for Classification
Problem
Solution
Discussion
7.10 Visualizing (Dis)Agreement
Problem
Solution
Discussion
7.11 Combining Models
Problem
Solution
Discussion
Chapter 8. Sequence-to-Sequence Mapping
8.1 Training a Simple Sequence-to-Sequence Model
Problem
Solution
Discussion
8.2 Extracting Dialogue from Texts
Problem
Solution
Discussion
8.3 Handling an Open Vocabulary
Problem
Solution
Discussion
8.4 Training a seq2seq Chatbot
Problem
Solution
Discussion
Chapter 9. Reusing a Pretrained Image Recognition Network
9.1 Loading a Pretrained Network
Problem
Solution
Discussion
9.2 Preprocessing Images
Problem
Solution
Discussion
9.3 Running Inference on Images
Problem
Solution
Discussion
9.4 Using the Flickr API to Collect a Set of Labeled Images
Problem
Solution
Discussion
9.5 Building a Classifier That Can Tell Cats from Dogs
Problem
Solution
Discussion
9.6 Improving Search Results
Problem
Solution
Discussion
9.7 Retraining Image Recognition Networks
Problem
Solution
Discussion
Chapter 10. Building an Inverse Image Search Service
10.1 Acquiring Images from Wikipedia
Problem
Solution
Discussion
10.2 Projecting Images into an N-Dimensional Space
Problem
Solution
Discussion
10.3 Finding Nearest Neighbors in High-Dimensional Spaces
Problem
Solution
Discussion
10.4 Exploring Local Neighborhoods in Embeddings
Problem
Solution
Discussion
Chapter 11. Detecting Multiple Images
11.1 Detecting Multiple Images Using a Pretrained Classifier
Problem
Solution
Discussion
11.2 Using Faster RCNN for Object Detection
Problem
Solution
Discussion
11.3 Running Faster RCNN over Our Own Images
Problem
Solution
Discussion
Chapter 12. Image Style
12.1 Visualizing CNN Activations
Problem
Solution
Discussion
12.2 Octaves and Scaling
Problem
Solution
Discussion
12.3 Visualizing What a Neural Network Almost Sees
Problem
Solution
Discussion
12.4 Capturing the Style of an Image
Problem
Solution
Discussion
12.5 Improving the Loss Function to Increase Image Coherence
Problem
Solution
Discussion
12.6 Transferring the Style to a Different Image
Problem
Solution
12.7 Style Interpolation
Problem
Solution
Discussion
Chapter 13. Generating Images with Autoencoders
13.1 Importing Drawings from Google Quick Draw
Problem
Solution
Discussion
13.2 Creating an Autoencoder for Images
Problem
Solution
Discussion
13.3 Visualizing Autoencoder Results
Problem
Solution
Discussion
13.4 Sampling Images from a Correct Distribution
Problem
Solution
Discussion
13.5 Visualizing a Variational Autoencoder Space
Problem
Solution
Discussion
13.6 Conditional Variational Autoencoders
Problem
Solution
Discussion
Chapter 14. Generating Icons Using Deep Nets
14.1 Acquiring Icons for Training
Problem
Solution
Discussion
14.2 Converting the Icons to a Tensor Representation
Problem
Solution
Discussion
14.3 Using a Variational Autoencoder to Generate Icons
Problem
Solution
Discussion
14.4 Using Data Augmentation to Improve the Autoencoder's Performance
Problem
Solution
Discussion
14.5 Building a Generative Adversarial Network
Problem
Solution
Discussion
14.6 Training Generative Adversarial Networks
Problem
Solution
Discussion
14.7 Showing the Icons the GAN Produces
Problem
Solution
Discussion
14.8 Encoding Icons as Drawing Instructions
Problem
Solution
Discussion
14.9 Training an RNN to Draw Icons
Problem
Solution
Discussion
14.10 Generating Icons Using an RNN
Problem
Solution
Discussion
Chapter 15. Music and Deep Learning
15.1 Creating a Training Set for Music Classification
Problem
Solution
Discussion
15.2 Training a Music Genre Detector
Problem
Solution
Discussion
15.3 Visualizing Confusion
Problem
Solution
Discussion
15.4 Indexing Existing Music
Problem
Solution
15.5 Setting Up Spotify API Access
Problem
Solution
Discussion
15.6 Collecting Playlists and Songs from Spotify
Problem
Solution
Discussion
15.7 Training a Music Recommender
Problem
Solution
15.8 Recommending Songs Using a Word2vec Model
Problem
Solution
Discussion
Chapter 16. Productionizing Machine Learning Systems
16.1 Using Scikit-Learn's Nearest Neighbors for Embeddings
Problem
Solution
Discussion
16.2 Use Postgres to Store Embeddings
Problem
Solution
Discussion
16.3 Populating and Querying Embeddings Stored in Postgres
Problem
Solution
Discussion
16.4 Storing High-Dimensional Models in Postgres
Problem
Solution
Discussion
16.5 Writing Microservices in Python
Problem
Solution
Discussion
16.6 Deploying a Keras Model Using a Microservice
Problem
Solution
Discussion
16.7 Calling a Microservice from a Web Framework
Problem
Solution
Discussion
16.8 TensorFlow seq2seq models
Problem
Solution
Discussion
16.9 Running Deep Learning Models in the Browser
Problem
Solution
Discussion
16.10 Running a Keras Model Using TensorFlow Serving
Problem
Solution
Discussion
16.11 Using a Keras Model from iOS
Problem
Solution
Discussion
Index
About the Author

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Deep Learning Cookbook

Description

More details

Other editions

Additional editions

Content

System requirements