Reference Library
The works behind our articles. Filter by framework and language. Openly-available sources link out; copyrighted works are cited for reference only.
27 of 27 references
- TextbookGeneralEN
Artificial Intelligence: A Modern Approach
Stuart Russell, Peter Norvig · Pearson (3rd edition) · 2010
The standard survey of artificial intelligence, organised around the idea of a rational agent. Covers uninformed and heuristic search, constraint satisfaction, adversarial search, logic and knowledge representation, probabilistic reasoning and Bayesian networks, Markov decision processes, reinforcement learning, and game theory, presenting algorithms as language-agnostic pseudocode.
Artificial IntelligenceSearch & PlanningKnowledge RepresentationProbabilityReference library (cite only) - TextbookREN
An Introduction to Statistical Learning, with Applications in R
Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani · Springer (Springer Texts in Statistics 103) · 2013
An accessible treatment of statistical learning that keeps the mathematics honest without assuming graduate-level background. Covers linear and logistic regression, resampling and cross-validation, subset selection and regularisation, tree-based methods, support vector machines, and unsupervised learning.
- TextbookPyTorchEN
Build a Large Language Model (From Scratch)
Sebastian Raschka · Manning · 2025
Implements a GPT-style language model end to end in PyTorch: text tokenisation and data sampling, the attention mechanism from first principles, the transformer architecture, pretraining on unlabelled text to obtain a foundation model, then fine-tuning it for classification and instruction following.
Generative AIDeep LearningNatural Language ProcessingReference library (cite only) - TextbookTensorFlow/KerasEN
Deep Learning with Python
François Chollet · Manning (2nd edition, MEAP) · 2020
A practical introduction to deep learning built around Keras, moving from the mathematical building blocks of neural networks through computer vision with convnets to sequence models and generative deep learning, with an emphasis on intuition over formalism.
Deep LearningComputer VisionProgrammingReference library (cite only) - TextbookREN
The Elements of Statistical Learning
Trevor Hastie, Robert Tibshirani, Jerome Friedman · Springer (2nd edition, Springer Series in Statistics) · 2009
The graduate companion to ISL, and the standard reference for statistical learning at full mathematical depth: linear methods for regression and classification, basis expansions and kernel smoothing, model assessment, additive models and trees, boosting, random forests, and unsupervised learning.
- TextbookGeneralEN
Deep Learning
Ian Goodfellow, Yoshua Bengio, Aaron Courville · MIT Press (Adaptive Computation and Machine Learning) · 2016
The reference text for deep learning, opening with the linear algebra, probability, and numerical computation the field assumes, then building through feedforward networks, regularisation, optimisation, convolutional and recurrent architectures, and the research frontier of generative models.
- TextbookGeneralEN
Reinforcement Learning: An Introduction
Richard S. Sutton, Andrew G. Barto · MIT Press (2nd edition) · 2018
The definitive treatment of reinforcement learning by two of its originators: bandits, Markov decision processes, dynamic programming, Monte Carlo methods, temporal-difference learning, eligibility traces, policy-gradient methods, and the approximate-solution methods that scale them.
- TextbookGeneralEN
Pattern Recognition and Machine Learning
Christopher M. Bishop · Springer (Information Science and Statistics) · 2006
A thoroughly Bayesian account of machine learning: probability distributions and conjugate priors, linear models for regression and classification, kernel methods, graphical models, mixture models and EM, variational inference, and sampling methods.
Machine LearningProbabilityStatisticsMathematicsReference library (cite only) - TextbookGeneralEN
Probabilistic Machine Learning: An Introduction
Kevin P. Murphy · MIT Press (Adaptive Computation and Machine Learning) · 2022
A modern, unified survey that treats machine learning as applied probability throughout, covering linear and logistic models, deep networks, structured prediction, and decision theory, with the author making a draft PDF and accompanying notebooks freely available.
- TextbookGeneralEN
Mathematics for Machine Learning
Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong · Cambridge University Press · 2020
Assembles exactly the mathematics machine learning depends on and no more: linear algebra, analytic geometry, matrix decompositions, vector calculus, probability, and continuous optimisation, then shows the four of them working together in regression, PCA, mixture models, and SVMs.
- TextbookGeneralEN
Convex Optimization
Stephen Boyd, Lieven Vandenberghe · Cambridge University Press · 2004
The standard reference on convex optimisation: convex sets and functions, how to recognise a problem as convex, duality and the KKT conditions, and the interior-point algorithms that solve such problems reliably at scale.
- TextbookGeneralEN
Information Theory, Inference, and Learning Algorithms
David J. C. MacKay · Cambridge University Press · 2003
Treats information theory, Bayesian inference, and learning as one subject: entropy and data compression, noisy-channel coding, Monte Carlo methods, and neural networks, argued through worked exercises rather than assertion.
- TextbookGeneralEN
Elements of Information Theory
Thomas M. Cover, Joy A. Thomas · Wiley (2nd edition) · 2006
The canonical graduate text on information theory: entropy and mutual information, asymptotic equipartition, data compression, channel capacity, differential entropy, rate distortion, and the connections to statistics and gambling.
Information TheoryProbabilityMathematicsReference library (cite only) - TextbookNumPyEN
Neural Networks and Deep Learning
Michael Nielsen · Determination Press · 2015
A short free online book that derives backpropagation carefully and builds a working digit classifier in plain NumPy, then explains why deep networks are hard to train and what the fixes actually do.
- TextbookGeneralEN
Speech and Language Processing
Dan Jurafsky, James H. Martin · Stanford (3rd edition draft, continuously revised)
The standard NLP textbook, spanning regular expressions and edit distance, n-gram and neural language models, sequence labelling, parsing and semantics, machine translation, and transformer-based large language models.
- TextbookGeneralEN
Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations
Yoav Shoham, Kevin Leyton-Brown · Cambridge University Press · 2009
Game theory written for computer scientists: normal- and extensive-form games, equilibrium concepts and how to compute them, social choice, mechanism and auction design, coalitional games, and logics of knowledge and belief.
- TextbookGeneralEN
Networks, Crowds, and Markets
David Easley, Jon Kleinberg · Cambridge University Press · 2010
Connects graph theory and game theory through the systems both describe: network structure and strong ties, games on networks, matching markets and auctions, information cascades, and the link analysis behind web search.
- StandardGeneralEN
AI Risk Management Framework (AI RMF 1.0)
National Institute of Standards and Technology · NIST (U.S. Department of Commerce) · 2023
A voluntary framework for identifying and managing the risks of AI systems, organised around four functions - govern, map, measure, and manage - and a set of characteristics a trustworthy system is expected to show.
- StandardGeneralEN
Regulation (EU) 2024/1689 laying down harmonised rules on artificial intelligence
European Parliament and Council of the European Union · Official Journal of the European Union · 2024
The EU AI Act: a risk-tiered regulation that prohibits certain practices outright, imposes conformity, documentation, and human-oversight duties on high-risk systems, and sets separate transparency obligations for general-purpose AI models.
- StandardGeneralEN
ISO/IEC 42001:2023 - Artificial intelligence management system
ISO/IEC JTC 1/SC 42 · International Organization for Standardization · 2023
The first certifiable management-system standard for artificial intelligence, specifying the processes an organisation must establish to develop and operate AI systems responsibly, in the same auditable form as ISO 9001 or 27001.
Artificial IntelligenceReference library (cite only) - GuideGeneralEN
Model Cards for Model Reporting
Margaret Mitchell, Simone Wu, Andrew Zaldivar, and others · ACM Conference on Fairness, Accountability, and Transparency (FAT*) · 2019
Proposes the short structured document that now ships with most released models: intended use, out-of-scope use, training data, and evaluation broken down by group rather than reported as a single aggregate number.
- GuideGeneralEN
Datasheets for Datasets
Timnit Gebru, Jamie Morgenstern, Briana Vecchione, and others · Communications of the ACM 64(12) · 2021
Argues that every dataset should ship with a datasheet recording why it was collected, from whom, how it was cleaned, and what it should not be used for, so that downstream model failures can be traced back to the data.
- TextbookEN
Understanding Machine Learning: From Theory to Algorithms
Shai Shalev-Shwartz, Shai Ben-David · Cambridge University Press · 2014
The standard modern treatment of learning theory: PAC learning, uniform convergence, the VC dimension and the fundamental theorem of statistical learning, no-free-lunch, and the bias-complexity trade-off, each stated as a theorem and proved rather than described. The reference behind the statistical-learning-theory path.
- TextbookEN
Trustworthy Online Controlled Experiments: A Practical Guide to A/B Testing
Ron Kohavi, Diane Tang, Ya Xu · Cambridge University Press · 2020
Written by the experimentation leads at Microsoft, Google and LinkedIn, and organised around the ways an online experiment misleads rather than the arithmetic of the t-test: peeking, metric proliferation, segment mining, variance reduction with pre-period covariates, and the institutional practice that keeps a result trustworthy. The reference behind the experimentation path.
StatisticsMachine LearningReference library (cite only) - TextbookEN
Recommender Systems: The Textbook
Charu C. Aggarwal · Springer · 2016
A systematic survey of recommendation: neighbourhood methods, matrix factorisation and its regularised variants, content-based and knowledge-based systems, evaluation beyond RMSE, cold start, and the attack and bias problems that come with deploying a recommender. The reference behind the recommender-systems path.
Machine LearningStatisticsReference library (cite only) - TextbookREN
Forecasting: Principles and Practice
Rob J Hyndman, George Athanasopoulos · OTexts · 2014
The standard applied forecasting text: stationarity and differencing, autocorrelation and the ARIMA family, exponential smoothing and decomposition, and evaluation on a forward split against a naive baseline. Example-led, with every method worked on real series.
- TextbookEN
Theory of Games and Economic Behavior
John von Neumann, Oskar Morgenstern · Princeton University Press (third edition, 1953; 1966 printing) · 1944
The book that founded game theory: the minimax theorem for zero-sum games, the axiomatic derivation of expected utility from preferences, and the theory of coalitions and stable sets for the n-person case. Dense and axiomatic rather than expository, and the primary source behind results the surveys state without proof.
MathematicsMachine LearningReference library (cite only)