Learning & reference for advanced learners
114 resources · page 4 of 4
NIST AI glossary
by NIST
NIST AI Resource Center glossary of trustworthy-AI terms from the AI Risk Management Framework, with references.
OECD AI Principles & AI system definition
by OECD
OECD.AI page on the OECD AI Principles and the OECD definition of an AI system.
Prince, Understanding Deep Learning
by udlbook
Simon Prince's Understanding Deep Learning textbook site with free PDF and Python notebooks.
Stanford CS25 Transformers United V6
Stanford CS25 Transformers United V6 seminar site with talks by researchers on transformer research.
Why Do Multi-Agent LLM Systems Fail?
by Mert Cemri et al. (UC Berkeley)
arXiv paper (2025) analysing why multi-agent LLM systems fail, with a taxonomy of 14 failure modes.
Wikipedia: Large language model
by Wikipedia (Wikimedia Foundation)
Wikipedia article on large language models: definition, history, architecture, training and limitations.
Yandex ML Handbook (Учебник по машинному обучению)
Yandex School of Data Analysis machine learning handbook in Russian, from classical algorithms to deep learning theory, with maths and code.
arXiv cs.AI recent
arXiv listing of recent papers in the cs.AI (Artificial Intelligence) category.
Attention Is All You Need
by Ashish Vaswani et al. (Google)
arXiv paper (2017) "Attention Is All You Need", introducing the Transformer architecture.
Convex Optimization
by Stephen Boyd and Lieven Vandenberghe (Stanford University)
Boyd and Vandenberghe's Convex Optimization book site with free PDF, slides and exercises.
Kraken
Kraken documentation: open-source text recognition system for historical and non-Latin scripts.
Language Models are Few-Shot Learners
by Tom B. Brown et al. (OpenAI)
arXiv paper (2020) "Language Models are Few-Shot Learners", introducing GPT-3 and in-context few-shot learning.
OpenNMT
by OpenNMT project (Harvard NLP and SYSTRAN)
OpenNMT site: open-source ecosystem for neural machine translation with training and deployment tools.
pgmpy
pgmpy documentation: Python library for probabilistic graphical models and causal inference.
Pyro
by Pyro project (Uber AI Labs)
Pyro: deep probabilistic programming library on PyTorch with inference tutorials.
Scaling Laws for Neural Language Models
by Jared Kaplan et al. (OpenAI)
arXiv paper (2020) "Scaling Laws for Neural Language Models", measuring power-law scaling of language model loss with size, data and compute.
scvi-tools
scvi-tools: library of probabilistic deep generative models for single-cell omics data.
Switch Transformers
by William Fedus et al. (Google)
arXiv paper (2021) introducing Switch Transformers, sparse mixture-of-experts models scaled to a trillion parameters.