Back to directory

Natural Language Processing: Neural Networks and Large Language Models

A book on neural networks and large language models for natural language processing, covering machine learning foundations through pre-training, generation, prompting, alignment, inference and reasoning.

Natural Language Processing: Neural Networks and Large Language Models

This is a book on neural networks and large language models in NLP, intended for anyone interested in NLP and deep learning, written by Tong Xiao and Jingbo Zhu. It is organized into three parts: preliminaries covering machine learning and neural network foundations, basic models such as word vectors, recurrent and convolutional sequence models, sequence-to-sequence models and transformers, and a part on large language models covering pre-training, generative models, prompting, alignment, inference and reasoning.

Chapters are available as individual PDFs alongside a complete combined PDF, and some material is drawn from the authors' earlier published articles with added new content. The book has also been translated into Chinese, Japanese, French, German, Italian and Portuguese using LLMs, with translations kept in a companion repository.

More in Books

See all 105
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • Samizdat

    rare-books.vercel.app

    A free, curated shelf of rare internal memos, leaked handbooks, and out-of-print books from technology and business history, collected for builders to read or borrow.

  • A free, web-only book that explains AI systems, from raw compute to a deployed and governed behavior, design-first, for a software engineer who knows distributed systems but is new to machine learning.