Deep learning is the latest trend in machine learning, but what exactly is deep learning, and how can we further our studies? To address these questions, this article lists 8 free deep learning books.
Deep Learning
(Deep Learning)
by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Also known as the “Flower Book,” this textbook on deep learning aims to help students and professionals enter the field of machine learning, particularly deep learning. The online version of the book has been completed and will continue to be available for free online reading.
English version:
http://www.deeplearningbook.org/
Chinese version:
https://github.com/exacity/deeplearningbook-chinese
Douban:
https://book.douban.com/subject/27087503/
Deep Learning Tutorial
(Deep Learning Tutorial)
by LISA Lab, University of Montreal
This book, written by the LISA Lab at the University of Montreal, explores the fundamentals of machine learning in a concise and free tutorial format. It emphasizes the use of Python through the Theano framework (developed by the university) to create deep learning models.
English version:
http://deeplearning.net/tutorial/deeplearning.pdf
Chinese version:
https://github.com/Syndrome777/DeepLearningTutorial
Deep Learning: Methods and Applications
(Deep Learning: Methods and Applications)
by Li Deng, Dong Yu, translated by Xie Lei
This book provides an overview of generic deep learning methods and their applications in various signal and information processing tasks.
English version:
https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/DeepLearning-NowPublishing-Vol7-SIG-039.pdf
Douban:
https://book.douban.com/subject/26815801/
First Contact with TensorFlow, Get Started with Deep Learning Programming
(First Contact with TensorFlow, Introduction to Deep Learning Programming)
by Jordi Torres
This book is aimed at engineers who have only a basic understanding of machine learning but want to apply their skills in the field of deep learning and practice using TensorFlow.
English version:
http://jorditorres.org/research-teaching/tensorflow/first-contact-with-tensorflow-book/
Neural Networks and Deep Learning
(NNDL, Neural Networks and Deep Learning)
by Michael Nielsen
This book will teach you about neural networks, a programming paradigm inspired by biology that allows computers to learn from observational data. It also covers a powerful set of learning techniques for neural networks—deep learning.
English version:
http://neuralnetworksanddeeplearning.com/index.html
Multiple Chinese versions:
https://legacy.gitbook.com/book/hit-scir/neural-networks-and-deep-learning-zh_cn/details
https://legacy.gitbook.com/book/xhhjin/neural-networks-and-deep-learning-zh/details
https://github.com/tigerneil/neural-networks-and-deep-learning-zh-cn
https://github.com/zhanggyb/nndl
Douban:
https://book.douban.com/subject/26727997/
A Brief Introduction to Neural Networks
(A Brief Introduction to Neural Networks)
by David Kriesel
This book discusses neural networks in depth. This biologically inspired data processing mechanism enables computers to learn in a human-like way, and after learning enough samples, it can generalize to solve more problems.
English version:
http://www.dkriesel.com/en/science/neural_networks
Neural Network Design, 2nd Edition
(Neural Network Design, 2nd Edition)
by Martin T. Hagan, Howard B. Demuth, Mark H. Beale, and Orlando D. Jess
This book provides a detailed overview of the structure and learning rules of neural networks. The authors emphasize understanding the main types of neural networks and their training methods. They also discuss the applications of neural networks in practical engineering problems such as pattern recognition, clustering, signal processing, and control systems. The book’s readability and smooth writing style are its strengths.
English version:
http://hagan.ecen.ceat.okstate.edu/nnd.html
Douban:
https://book.douban.com/subject/1115600/
Neural Networks and Learning Machines, 3rd Edition
(Neural Networks and Learning Machines, 3rd Edition)
by Simon Haykin
This book is in its third edition, and the author provides the latest processing methods for neural networks in a comprehensive, transparent, and easy-to-read manner, dividing it into three chapters. The book starts with classical supervised learning, then transitions to kernel-based RBF (radial-basis function) networks, and finally focuses on the core of machine learning—regularization theory.
English version:
https://cours.etsmtl.ca/sys843/REFS/Books/ebook_Haykin09.pdf
Douban:
https://book.douban.com/subject/5952531
Translation: Leo
Reviewed by: Nonlinear
Edited by: Queen
Original article:
https://www.kdnuggets.com/2018/04/top-free-books-deep-learning.html
Follow the Swarm AI Academy WeChat account
to get more interesting AI tutorials!
Search WeChat account: swarmAI
Swarm AI Academy QQ group: 426390994
Academy website: campus.swarma.org
Business cooperation and contributions and reprints｜[email protected]