Deep Learning Cookbook: Practical Recipes to Get Started Quickly

Deep learning doesn’t have to be intimidating. Until recently, this machine-learning method required years of study, but with frameworks such as Keras and Tensorflow, software engineers without a background in machine learning can quickly enter the field. With the recipes in this cookbook, you’ll learn how to solve deep-learning problems for classifying and generating text, images, and music.

Each chapter consists of several recipes needed to complete a single project, such as training a music recommending system. Author Douwe Osinga also provides a chapter with half a dozen techniques to help you if you’re stuck. Examples are written in Python with code available on GitHub as a set of Python notebooks.

You’ll learn how to:

• Create applications that will serve real users
• Use word embeddings to calculate text similarity
• Build a movie recommender system based on Wikipedia links
• Learn how AIs see the world by visualizing their internal state
• Build a model to suggest emojis for pieces of text
• Reuse pretrained networks to build an inverse image search service
• Compare how GANs, autoencoders and LSTMs generate icons
• Detect music styles and index song collections

Table of Contents

Chapter 1. Tools and Techniques
Chapter 2. Getting Unstuck
Chapter 3. Calculating Text Similarity Using Word Embeddings
Chapter 4. Building a Recommender System Based on Outgoing Wikipedia Links
Chapter 5. Generating Text in the Style of an Example Text
Chapter 6. Question Matching
Chapter 7. Suggesting Emojis
Chapter 8. Sequence-to-Sequence Mapping
Chapter 9. Reusing a Pretrained Image Recognition Network
Chapter 10. Building an Inverse Image Search Service
Chapter 11. Detecting Multiple Images
Chapter 12. Image Style
Chapter 13. Generating Images with Autoencoders
Chapter 14. Generating Icons Using Deep Nets
Chapter 15. Music and Deep Learning