Deep Learning Cookbook: Practical Recipes to Get Started Quickly

Deep learning doesnÃ?Â[ 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, youÃ?Â[ 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 youÃ?Â[ re stuck. Examples are written in Python with code available on GitHub as a set of Python notebooks.

YouÃ?Â[ 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

Author: Douwe Osinga
Publisher: O'Reilly Media
Published: 07/17/2018
Pages: 251
Binding Type: Paperback
Weight: 0.90lbs
Size: 9.10h x 7.00w x 0.50d
ISBN: 9781491995846

About the Author

Douwe Osinga is an experienced Software Engineer, formerly with Google, and founder of three startups. He maintains a popular software project website, partly focused on machine learning(https: //douweosinga.com/projects/​machine_learning).