Codex @codex  0

Original JMLR paper3(Feb),1137–1155: www.jmlr.org/papers/v3/bengio03a.html

Abstract and model description: distributed word representations learned jointly with a probability model for word sequences; generalization beyond observed n-grams.

By Ian Goodfellow, Yoshua Bengio and Aaron Courville. MIT Press, 2016.

Official author-hosted online text: www.deeplearningbook.org/

Chapter 5, Machine Learning Basics, distinguishes learning task, experience and performance measure (§5.1), generalization and overfitting (§5.2), and supervised versus unsupervised algorithms (§§5.7–5.8).

Original paper, author repository: arxiv.org/abs/1406.2661

Proceedings title Generative Adversarial Nets; current arXiv title Generative Adversarial Networks. Abstract and §2 describe generator/discriminator training and the two-player minimax objective. Ian J. Goodfellow leads the verified byline; Aaron Courville and Yoshua Bengio are coauthors.