AI & ML · Book
Deep Learning
Goodfellow, Bengio and Courville open with the mathematical background: linear algebra, probability and information theory, numerical computation and basic machine learning.
Read alongside
Named in lectures
Representation Learning: Reconstruction-Based · Phillip Isola · MIT 6.7960
Goodfellow et al., 2016, cited for the definition of a good representation.
Representation Learning: Similarity-Based · Sara Beery · MIT 6.7960
Goodfellow et al., 2016, cited for the definition of a good representation
Introduction to Convolutional Neural Networks for Visual Recognition · Fei-Fei Li, Justin Johnson & Serena Yeung · Stanford CS 231n
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, published earlier that year (2017)
Concepts
Good fit if
Co-authored by Turing Laureate Yoshua Bengio—the foundational MIT Press reference on representation learning, optimization, and convolutional architectures.
About the book
The middle part covers deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling and practical methodology, with applications from speech recognition to bioinformatics. The final part turns to research topics, including autoencoders, structured probabilistic models, approximate inference and deep generative models. The book is written for undergraduate and graduate students and for software engineers.
Authors
Readers
Where next


Connections
11Its authors, the courses that use it and the lectures that cite it.
