"This book is a stunning achievement, written with precision and depth of understanding. It entertains you and gives you lots of interesting information at the same time. I could never imagine understanding and gaining scientific knowledge, namely 'Deep Learning' can be this much fun! Reading the book is a pleasure and I highly recommend it."
-maryamkhakpour, O'Reilly Online Learning (Safari) Reviewer
"This title is a great resource for those looking to understand deep learning. The illustrations are helpful and aid in cementing a richer understanding of the content, and the background context surrounding biological motivations for the tools and techniques enables a greater appreciation of the field. I enthusiastically recommend this book to any and all who are interested in the topic of deep learning."
-vincepetaccio, O'Reilly Online Learning (Safari) Reviewer
Deep learning is transforming software, facilitating powerful new artificial intelligence capabilities, and driving unprecedented algorithm performance. Deep Learning Illustrated is uniquely visual, intuitive, and accessible, and yet offers a comprehensive introduction to the discipline's techniques and applications. Packed with full-color applications and easy-to-follow code, it sweeps away much of the complexity of building deep learning models, making the subject approachable and fun to learn.

World-class instructor and practitioner Jon Krohn-with crucial material from Grant Beyleveld and beautiful illustrations by Aglae Bassens-presents straightforward analogies to explain what deep learning is, why it has become so popular, and how it relates to other machine learning approaches. He also offers a practical reference and tutorial for developers, data scientists, researchers, analysts, and students who want to start applying it. He covers essential theory with as little mathematics as possible, preferring to illuminate concepts with hands-on Python code and practical "run-throughs" in accompanying Jupyter notebooks. To help you progress quickly, he focuses on the versatile, high-level deep learning library Keras to nimbly construct efficient TensorFlow models; PyTorch, the leading alternative library, is also covered.

You'll gain a pragmatic und