Book

Deep learning cookbook : practical recipes to get started quickly / Douwe Osinga.

Summary:

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.

Record details

ISBN: 149199584X
ISBN: 9781491995846
Physical Description: xv, 234 pages : illustrations ; 24 cm.
Edition: First edition.
Publisher: Sebastopol, CA : O'Reilly Media, 2018.
Copyright: ©2018.

Content descriptions

General Note:

Includes index.

Formatted Contents Note:

Tools and techniques -- Getting unstuck -- Calculating text similarity using word embeddings -- Building a recommender system based on outgoing Wikipedia links -- Generating text in the style of an example text -- Question matching -- Suggesting emojis -- Sequence-to-sequence mapping -- Reusing a pretrained image recognition network -- Building an inverse image search service -- Detecting multiple images -- Image style -- Generating images with autoencoders -- Generating icons using deep nets -- Music and deep learning -- Productionizing machine learning systems.