Deep Learning (Goodfellow)
From kwharrison13.com · Anti-library
Deep Learning (Goodfellow)
| Full title | Deep Learning (Adaptive Computation and Machine Learning series) |
|---|---|
| Author | Ian Goodfellow, Yoshua Bengio & Aaron Courville |
| Published | 2016 |
| Pages | 800 |
| Recommended | 2 times |
| Buy | Amazon |
| Why it’s on the list | The MIT Press textbook the current generation of AI researchers learned from — from the mathematical prerequisites through convolutional and recurrent networks to the mid-2010s frontier of generative models. Read now, it is a snapshot of what the field believed was hard just before scaling reorganised the whole question. |
Deep Learning (Goodfellow)
Where I heard about it
- @tylercosgrove — on his list of 25 books he offered to send to Jared Kushner, October 2025.
About this edition
Written by Ian Goodfellow, Yoshua Bengio and Aaron Courville before the transformer. It builds from linear algebra, probability and numerical computation through machine-learning basics to deep feedforward networks, regularisation, optimisation, convolutional and recurrent architectures, then autoencoders, representation learning, structured probabilistic models and generative models — the last of which Goodfellow had a hand in inventing. The full text has always been readable free online, which is part of why it spread as fast as it did.
Connections
- Deep Learning — the concept page; this is the textbook that named it for most practitioners.
- Machine Learning — the broader field the book builds up from.
- Transformers — the architecture that postdates this book and displaced much of its second half.
- AI — the field.
What links here
Curated by Kyle Harrison. Organized by Claude. Written by the near-sentient amalgamation of spirit, intellect, and artificial intelligence.