Deepmath : Mathématiques des réseaux de neurones
by Arnaud Bodin, François Recher · Exo7 (Université de Lille)
Free Exo7 textbook from Université de Lille that builds the mathematics of neural networks from first-year level: derivatives, gradients, gradient descent, backpropagation, convolution, tensors and probability, with Python/Keras chapters applying each idea.
More resources on Mathematics for Machine Learning
StatQuest with Josh Starmer
YouTube channel by Josh Starmer that explains statistics and machine learning step by step, from p-values, linear models and ANOVA to PCA, decision trees, neural networks and transformers. Viewers build clear intuition for how common methods work before tackling the math.
Practical Statistics for Data Scientists
A concise statistics book written for programmers that covers sampling, experimental design, A/B testing, regression, classification, and resampling, with R code throughout. Readers learn which statistical ideas matter for data science and how sampling and study design shape the conclusions data can support.
Matrix Calculus for Machine Learning and Beyond (MIT 18.S096)
Extends calculus to matrices and general vector spaces: derivatives as linear operators, Jacobians, derivatives of matrix factorizations, adjoint methods and automatic differentiation. 17 lecture videos, lecture notes, and problem sets with solutions teach learners to derive and compute gradients for large-scale optimization.
Las matemáticas de la inteligencia artificial
Open university text from Universidad Complutense de Madrid building the maths behind neural networks: multivariable calculus, chain rule, gradient descent and Adam, backpropagation and training. Free online, taught in Spanish; still marked as a draft.
Statistik und maschinelles Lernen: Eine mathematische Einführung in klassische und moderne Methoden
Proof-based German textbook linking mathematical statistics to machine learning. Analyses classical estimators and modern classification methods with non-asymptotic bounds, bridging to current research, with exercises at the end of each chapter. Written for mathematics students.
機械学習のための連続最適化
Kodansha Machine Learning Professional Series volume on continuous optimization for ML: convex analysis, gradient and Newton methods, duality, proximal and stochastic methods, with applications to regression, SVMs and sparse learning.