Skip to content

mathematics-for-ai.md

Latest commit

 

History

History
322 lines (247 loc) · 29.9 KB

mathematics-for-ai.md

File metadata and controls

322 lines (247 loc) · 29.9 KB

🔢 Mathematics for AI and Machine Learning

Essential mathematical foundations including linear algebra, calculus, probability, and statistics for understanding AI and ML algorithms.

📖 Overview

Mathematics forms the theoretical foundation of AI and machine learning. Understanding linear algebra, calculus, probability, and optimization is crucial for comprehending how algorithms work, implementing models from scratch, and advancing research. Recent 2025 advances include practical probability engineering approaches for deep learning and comprehensive reviews of statistics in the AI era.

Keywords: mathematics-for-machine-learning, linear-algebra, calculus, probability-theory, statistics, optimization, matrix-computation, gradient-descent, mathematical-foundations, ml-math, probability-engineering, statistics-ai-era, deep-learning-theory, 2025

Skill Levels: 🟢 Beginner | 🟡 Intermediate | 🔴 Advanced

📚 Topics Covered

  • Linear algebra (vectors, matrices, eigenvalues, eigenvectors)
  • Calculus (derivatives, gradients, optimization)
  • Probability theory and statistics
  • Multivariate calculus and matrix calculus
  • Optimization theory (convex optimization, gradient methods)
  • Information theory
  • Markov chains and stochastic processes
  • Discrete mathematics and graph theory
  • Probability engineering and randomness modeling
  • Statistical foundations of deep learning
  • Bayesian inference and variational methods
  • Meta-statistical learning and distribution-level inference

⭐ Starter Kit (Absolute Beginners Start Here)

If you're completely new to Mathematics for AI, start with these 3 resources in order:

  1. 🟢 Khan Academy - Linear Algebra - Interactive fundamentals with visual explanations and practice exercises
  2. 🟢 3Blue1Brown - Essence of Linear Algebra - Beautiful visual intuition for 15 core linear algebra concepts
  3. 🟡 Khan Academy - Calculus - Build towards derivatives and integrals with step-by-step explanations

After completing the starter kit, explore the full resources below.

📕 Textbooks & Books

🟡 Intermediate

  • Mathematics for Machine Learning (Cambridge University Press) (Intermediate) - Comprehensive 412-page free textbook by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong covering linear algebra, analytic geometry, matrix decompositions, vector calculus, probability, optimization, and their direct applications to machine learning.

    • 📖 Access: Fully open, Direct PDF download
    • 🌍 Authority: Cambridge University Press (official textbook)
    • [Tags: textbook linear-algebra calculus probability official]

  • Deep Learning Book - Mathematical Basics (Intermediate/Advanced) - Free foundational chapters from the Deep Learning textbook by Ian Goodfellow, Yoshua Bengio, and Aaron Courville covering applied math essentials: linear algebra, probability, numerical computation, and machine learning basics.

    • 📖 Access: Fully open, online HTML format
    • 🌍 Authority: MIT Press (Goodfellow, Bengio, Courville)
    • [Tags: deep-learning-math applied-math probability]

  • Finite Markov Chains and Monte-Carlo Methods: An Undergraduate Introduction (Intermediate) - Free comprehensive textbook for one-semester course on Markov chains, suitable for undergraduates with basic probability and linear algebra knowledge. Covers finite-state chains, classical models, asymptotic behavior, mixing times, Monte Carlo methods, martingales, and harmonic functions with 100+ exercises and illustrations.

    • 📖 Access: Free PDF (arXiv)
    • 🎯 Topics: Markov chains, mixing times, Monte Carlo simulation, martingales
    • [Tags: intermediate markov-chains monte-carlo probability textbook 2025]

🔴 Advanced

  • Matrix Calculus for Machine Learning and Beyond (MIT 18.S096) ⭐ 2025 MIT COURSE - Comprehensive undergraduate-level course from MIT introducing differential calculus extended to vector spaces. Covers derivatives for large-scale optimization, efficient derivative propagation methods, and computational applications in machine learning. Emphasizes practical implementations and matrix/tensor operations essential for deep learning. Full course materials with lecture notes and problem sets.

    • 📖 Access: Free PDF (full course materials, arXiv)
    • 🌍 Authority: MIT Mathematics Department (official course 18.S096)
    • 📝 Topics: Matrix derivatives, Jacobians, Hessians, automatic differentiation, optimization algorithms
    • 🛠️ Hands-on: Yes (with implementations)
    • [Tags: advanced matrix-calculus optimization gradient-computation mit autograd 2025]

  • Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI (Advanced) ⭐ 2025 RESEARCH - Cutting-edge arXiv paper from March 2025 proposing probability engineering as fundamental paradigm for modern deep learning. Demonstrates how explicit probabilistic modeling, uncertainty quantification, and stochastic sampling enhance neural networks beyond standard backpropagation. Covers Bayesian deep learning, variational inference, normalizing flows, diffusion models, and energy-based models with practical implementation insights. Bridges classical probability theory and modern generative AI.

    • 📖 Access: Free on arXiv (HTML format)
    • 🔬 Novel: Practical probability engineering for modern AI
    • 📝 Topics: Uncertainty quantification, variational inference, diffusion models, energy-based models, Bayesian deep learning
    • 🧠 Emerging field: Probability engineering as ML paradigm
    • [Tags: advanced probability-engineering deep-learning uncertainty bayesian arxiv 2025]

  • Applied Statistics in the Era of Artificial Intelligence: A Review and Vision (Advanced) - Comprehensive 2024 research review examining how classical statistics is evolving in context of AI and machine learning. Covers estimation, inference, causal inference, experimental design, robustness, and applications in generative models. Addresses tensions between statistical rigor and ML scalability with vision for future of AI-enhanced statistics and statistics-grounded AI.

    • 📖 Access: Free PDF (arXiv)
    • 🔬 Analysis: Statistics meets AI era
    • 📝 Topics: Bayesian inference, causal inference, robustness, experimental design, generative models
    • 🌟 Vision: Unified statistics-AI future
    • [Tags: advanced statistics ai-era causal-inference bayesian robustness arxiv 2024]

  • Meta-Statistical Learning: Supervised Learning of Statistical Inference (arXiv Feb 2025) (Advanced) ⭐ FEBRUARY 2025 - Cutting-edge research demonstrating how LLM principles can tackle distribution-level tasks (parameter estimation, hypothesis testing, mutual information estimation) rather than individual datapoint predictions. Proposes meta-statistical learning framework inspired by multi-instance learning, enabling supervised learning for statistical inference problems. Bridges deep learning and classical statistics.

    • 📖 Access: Free PDF (arXiv)
    • 🔬 Novel: Meta-statistical learning framework for distribution-level inference
    • 📝 Topics: Statistical inference, parameter estimation, hypothesis testing, mutual information, distribution-level learning
    • 🧠 Innovation: Applying LLM tools to statistics
    • [Tags: advanced meta-learning statistical-inference llm-principles distribution-learning arxiv 2025]

🎓 Courses & Video Lectures

🟢 Beginner-Friendly

  • Khan Academy - Linear Algebra (Beginner) - Free comprehensive interactive course covering vectors, matrices, matrix transformations, determinants, and essential linear algebra concepts for ML with practice exercises and visual explanations.

    • 📖 Access: Fully open, interactive
    • [Tags: beginner interactive linear-algebra fundamentals]

  • Khan Academy - Calculus (Beginner) - Free complete calculus curriculum including limits, derivatives, integrals, differential equations, and multivariate calculus with step-by-step instruction and practice problems.

    • 📖 Access: Fully open, interactive
    • [Tags: beginner calculus derivatives integrals]

  • Khan Academy - Probability & Statistics (Beginner) - Comprehensive free course covering probability fundamentals, random variables, distributions, statistical inference, hypothesis testing, confidence intervals, and regression analysis with interactive exercises and real-world examples essential for understanding ML algorithms.

    • 📖 Access: Fully open, interactive platform
    • 🌍 Authority: Khan Academy
    • 📝 Topics: Probability, distributions, hypothesis testing, regression, statistical inference
    • [Tags: beginner probability statistics interactive hypothesis-testing regression 2025]

  • 3Blue1Brown - Essence of Linear Algebra (Beginner/Intermediate) - Beautiful 15-video series providing geometric intuition for linear algebra concepts including vectors, span, linear transformations, determinants, eigenvectors, and their significance in ML through stunning animations. Now with interactive exercises!

    • 📖 Access: Free on YouTube + interactive exercises at 3Blue1Brown.com
    • 📝 Format: 15 animated video lessons (~3 hours total)
    • 🎯 Topics: Vectors, transformations, eigenvalues, determinants, applications
    • ✨ New: Interactive exercises now available directly on videos
    • [Tags: beginner intermediate visual-learning linear-algebra animations interactive 2025]

  • 3Blue1Brown - Essence of Calculus (Beginner/Intermediate) - 12-part video series building intuition for calculus fundamentals: derivatives, chain rule, integrals, Taylor series, and their connection to neural networks and optimization.

    • 📖 Access: Free on YouTube
    • [Tags: beginner calculus visual-learning gradients]

  • Mathematics for Machine Learning - Simplilearn SkillUp (Beginner to Intermediate) - Comprehensive free course covering essential mathematical foundations for ML: linear algebra (vectors, matrices, eigenvalues), calculus (derivatives, gradients), probability theory, and statistics. Includes certificate upon completion. Perfect for ML beginners building mathematical intuition without prerequisites.

    • 📖 Access: Free with certificate option
    • 📝 Duration: Self-paced (approximately 8 hours)
    • 🎯 Topics: Linear algebra, calculus, probability, statistics for ML
    • [Tags: beginner intermediate linear-algebra calculus probability certificate 2025]

  • Introduction to Linear Algebra (Alison) (Beginner) - Free self-paced online course introducing linear algebra fundamentals for data science and machine learning applications. Covers solving systems of linear equations, linear transformations, eigenvalues/eigenvectors of matrices, and their practical applications with certificate option.

    • 📖 Access: Free (certificate option available)
    • 🎯 Best for: Data science preparation, practical linear algebra applications
    • [Tags: beginner linear-algebra systems-equations transformations certificate 2025]

  • Brilliant - Calculus Fundamentals (Beginner to Intermediate) - Interactive course teaching calculus through hands-on problem-solving and visual explanations. Covers limits, derivatives, integrals, and optimization with immediate feedback and intuitive visualizations perfect for building mathematical intuition needed for gradient-based ML algorithms.

    • 📖 Access: Free basic access (premium features available)
    • 🛠️ Hands-on: Yes (interactive problem-solving)
    • 🎯 Topics: Limits, derivatives, integrals, optimization, applications
    • [Tags: beginner intermediate calculus interactive visual-learning optimization 2025]

🟡 Intermediate

  • Math for AI: Linear Algebra, Calculus & Optimization Guide (GUVI 2025) (Intermediate) - Comprehensive 2025 guide connecting mathematical foundations directly to AI applications. Covers linear algebra for neural networks (vectors, matrices, transformations, eigenvalues), calculus for optimization (derivatives, gradients, backpropagation), probability & statistics (distributions, Bayesian methods), and optimization algorithms (gradient descent, regularization). Each concept linked to real ML use cases with practical examples.

    • 📖 Access: Fully free online guide
    • 🏛️ Authority: GUVI (Intel-certified education platform)
    • 🎯 Topics: Linear algebra, calculus, optimization, probability, statistics, matrix operations, gradient descent
    • 🔗 Applications: Neural networks, deep learning, model optimization
    • [Tags: intermediate guide 2025 linear-algebra calculus optimization ml-applications practical guvi]

  • AI and Machine Learning Certificate Program (UT Austin Online) (Intermediate to Advanced) - Professional certificate program covering Python foundations, statistical learning, machine learning algorithms (supervised/unsupervised), deep learning, computer vision, NLP, and recommendation systems. Includes mathematical foundations (linear algebra, calculus, statistics) with hands-on implementation using NumPy, Pandas, TensorFlow, Keras. Self-paced modules with multimodal generative AI component.

    • 📖 Access: Paid program (check for free modules/trials)
    • 🏛️ Authority: University of Texas at Austin (McCombs School of Business)
    • 🎯 Topics: Python, statistics, ML algorithms, deep learning, CNNs, NLP, recommendation systems, SQL
    • 📄 Certificate: Professional certificate from UT Austin
    • ⚠️ Note: Primarily paid, but foundational modules may have free access
    • [Tags: intermediate advanced ut-austin ml-certificate python tensorflow deep-learning 2024]

  • Mathematics for Machine Learning and Data Science Specialization (DeepLearning.AI) (Beginner to Intermediate) - Beginner-friendly 3-course specialization by DeepLearning.AI covering calculus, linear algebra, statistics, and probability essentials for ML. Topics include systems of linear equations, eigenvalues/eigenvectors, PCA, Bayesian statistics, maximum likelihood estimation, and hypothesis testing with ML motivations throughout. Created by Andrew Ng's team.

    • 📖 Access: Free audit available on Coursera (certificate paid)
    • 🌍 Authority: DeepLearning.AI (Andrew Ng)
    • 📝 Includes: 3 courses - Linear Algebra, Calculus, Probability & Statistics
    • ⚠️ Note: Requires free Coursera account for audit
    • [Tags: beginner intermediate andrew-ng deeplearning-ai coursera pca bayesian 2025]

  • Mathematics for Machine Learning (Coursera, Imperial College London) (Beginner/Intermediate) - Free foundational specialization from Imperial College London (via Coursera) that covers essential linear algebra, multivariate calculus, and PCA (Principal Component Analysis) concepts for AI/ML. Suitable for absolute beginners and those refreshing core math skills for machine learning. Audit for free (certificate available with fee).

    • 📖 Access: Free audit available (certificate requires fee)
    • 🏛️ Source: Imperial College London (Coursera)
    • 🐨 Instructors: Imperial College London faculty
    • ⚠️ Note: Requires free Coursera account
    • [Tags: beginner intermediate mathematics-for-ai linear-algebra calculus statistics machine-learning imperial-college-london free-course fundamentals 2025]

  • Mathematics for Artificial Intelligence and Machine Learning (Harvard Extension) (Intermediate to Advanced) ⭐ SPRING 2026 - Comprehensive Harvard course teaching mathematics needed to understand how AI works under the hood. Covers intensive review of linear algebra, analytic geometry, vector calculus, optimization, and probability, then applies them to ML methods like regression, dimensionality reduction (PCA), density estimation with Gaussian mixture models, and classification with support vector machines. Designed for developers and practitioners bridging math knowledge and ML methods.

    • 📖 Access: Course info freely available (enrollment for credit requires registration)
    • 🏛️ Authority: Harvard University (Division of Continuing Education)
    • 🎓 Credits: 4 graduate/undergraduate/noncredit
    • 📝 Topics: Linear algebra, vector calculus, optimization, probability, PCA, SVMs, regression, GMMs
    • ⏱️ Term: Spring 2026, Full Term, Live Web Conference
    • [Tags: intermediate advanced harvard spring-2026 linear-algebra optimization probability ml-methods 2026]

  • MIT OpenCourseWare - Linear Algebra (18.06) by Gilbert Strang (Intermediate) - Legendary MIT course covering matrix operations, vector spaces, eigenvalues, positive definite matrices, and applications with full lecture videos, assignments, and exams. One of the most popular math courses for ML practitioners.

    • 📖 Access: Fully open, MIT OCW
    • 🌍 Authority: MIT (Professor Gilbert Strang)
    • [Tags: intermediate university-course linear-algebra mit]

  • MIT 18.05: Introduction to Probability and Statistics (Spring 2022) (Intermediate) ⭐ UPDATED SPRING 2022 - Official MIT OpenCourseWare course covering probability foundations and statistics essentials for data science and machine learning. Covers probability axioms, random variables, distributions, Bayesian inference, hypothesis testing, confidence intervals, and regression with full lecture notes, recitation videos, assignments, exams, and interactive components. Updated 2022 with latest course materials including reading questions and problem checkers.

    • 📖 Access: Fully open, MIT OCW + Open Learning Library
    • 🌍 Authority: MIT Mathematics Department
    • 📝 Topics: Probability theory, Bayesian inference, hypothesis testing, statistical inference, regression, R programming
    • 🎥 Format: Lecture notes, videos, problem sets, exams with solutions, interactive components
    • ⏱️ Duration: Full semester course (13+ weeks)
    • [Tags: intermediate mit probability statistics bayesian-inference hypothesis-testing confidence-intervals r-programming 2022-2025]

  • Stanford CS229 Math Resources (Intermediate) - Comprehensive collection of mathematical review materials from Stanford's legendary machine learning course covering linear algebra, probability theory, convex optimization, and hidden Markov models with detailed notes and problem sets designed specifically for ML applications.

    • 📖 Access: Fully open, course website
    • 🌍 Authority: Stanford University (CS229)
    • 📝 Includes: Linear algebra review, probability review, convex optimization I & II
    • [Tags: intermediate stanford machine-learning linear-algebra probability optimization 2025]

  • Stanford EE364A - Convex Optimization I (Intermediate to Advanced) - Legendary Stanford graduate course covering convex sets, functions, optimization problems, duality theory, and algorithms including gradient descent and Newton's method. Essential for understanding optimization in machine learning with full lecture videos, assignments, and extensive problem sets from Professor Stephen Boyd.

    • 📖 Access: Fully open via Stanford Engineering Everywhere
    • 🌍 Authority: Stanford University (Professor Stephen Boyd)
    • 📝 Includes: Full lecture videos, slides, homework, exams
    • 🎯 Topics: Convex sets, functions, optimization, duality, algorithms
    • [Tags: intermediate advanced stanford convex-optimization gradient-descent algorithms boyd 2025]

  • MIT 6.042J - Mathematics for Computer Science (Intermediate) - Comprehensive MIT OpenCourseWare covering discrete mathematics fundamentals including proofs, graphs, state machines, modular arithmetic, counting, and discrete probability theory essential for understanding algorithms, computability, and machine learning theory with full lecture videos, problem sets, and exams.

    • 📖 Access: Fully open, MIT OCW
    • 🌍 Authority: MIT
    • 📝 Includes: Video lectures, problem sets, exams with solutions
    • [Tags: intermediate discrete-math probability computer-science mit fundamentals 2025]

  • Probability & Statistics for Machine Learning & Data Science (Coursera) (Intermediate) - Free course (audit mode) covering probability distributions, Bayesian statistics, hypothesis testing, and statistical inference essential for ML. Learn the law of large numbers, central limit theorem, point estimation, maximum likelihood estimation, confidence intervals, and Bayesian approaches with visual and intuitive explanations.

    • 📖 Access: Free to audit (certificate paid)
    • 📝 Duration: Self-paced, approximately 25 hours
    • 🎯 Topics: Probability, Bayesian stats, hypothesis testing, central limit theorem
    • [Tags: intermediate coursera probability statistics bayesian inference 2025]

  • Probability Theory (TU Delft - edX) (Intermediate) - Comprehensive 6-week self-paced course introducing probability theory with focus on interpretation rather than computation. Covers discrete/continuous random variables, probability distributions, joint distributions, multivariate random variables, law of large numbers, central limit theorem, and Monte Carlo simulation through the Grasple platform with intelligent feedback.

    • 📖 Access: Fully open, edX/Grasple platform
    • 🌍 Authority: Delft University of Technology (Netherlands)
    • 📝 Duration: 6 weeks, 4-6 hours per week
    • 🛠️ Hands-on: Yes (with interactive exercises)
    • [Tags: intermediate probability-theory random-variables monte-carlo simulation interactive 2025]

  • Statistics for Data Science & Machine Learning (YouTube) (Intermediate) - Free comprehensive YouTube video (70+ minutes) covering essential statistics concepts for data science: categorical/numerical data, distributions, mean/median/mode, variance/standard deviation, correlation/covariance, probability distributions, normal distribution, central limit theorem, confidence intervals, t-tests, and hypothesis testing. Perfect quick reference for ML practitioners.

    • 📖 Access: Free on YouTube
    • 📝 Duration: 70+ minutes
    • 🎯 Topics: Descriptive statistics, hypothesis testing, confidence intervals, distributions, correlation
    • [Tags: intermediate youtube statistics distributions hypothesis-testing confidence-intervals 2025]

🛠️ Tools & Implementation

🟡 Intermediate

  • Math for AI - Comprehensive GitHub Repository (2025) (Beginner to Advanced) ⭐ MARCH 2025 - Comprehensive open-source GitHub repository covering all math concepts needed for AI from fundamentals to advanced topics. Includes supervised learning (linear/logistic regression, SVMs, neural networks with PyTorch), unsupervised learning (clustering, PCA), learning theory (optimization, overfitting, bias-variance), and advanced topics (distributed learning, online learning, reinforcement learning, transformers). Well-organized with code examples and practical implementations.

    • 📖 Access: Fully open on GitHub, free
    • 🛠️ Hands-on: Yes (PyTorch implementations)
    • 🎯 Topics: Linear algebra, calculus, probability, optimization, supervised/unsupervised learning, neural networks, transformers
    • 📚 Coverage: Fundamentals → Advanced (comprehensive)
    • [Tags: intermediate advanced github open-source pytorch neural-networks transformers comprehensive 2025]

  • PyTorch Official Tutorials (Beginner/Intermediate) - Official comprehensive PyTorch tutorials covering tensor mathematics, automatic differentiation, neural network building blocks, and practical implementation of mathematical concepts in deep learning including linear algebra operations, gradient computation, and optimization algorithms with runnable code examples.

    • 📖 Access: Fully open, official documentation
    • 🌍 Authority: PyTorch (official)
    • 🛠️ Hands-on: Yes (interactive code examples)
    • 💻 Topics: Tensors, autograd, neural networks, optimization
    • [Tags: intermediate pytorch tensors autograd hands-on implementation 2025]

  • Engineer4Free Linear Algebra Course (Beginner to Intermediate) - Free online linear algebra course with 56 tutorials covering introductory concepts in vectors and matrix algebra. Structured as a typical first-year university linear algebra course with tutorials progressing from basic concepts to more advanced topics, making it ideal for self-paced learning.

    • 📖 Access: Fully open online
    • 📝 Duration: 56 video tutorials, self-paced
    • 🎯 Topics: Vectors, matrices, transformations, eigenvalues, applications
    • [Tags: beginner intermediate linear-algebra vectors matrices free-course 2025]

📦 Interactive Learning Platforms

🟢 Beginner-Friendly

  • Probability Fundamentals (Brilliant.org) (Beginner to Intermediate) - Interactive probability course teaching how to represent and interpret data and events using probability. Covers estimating probabilities, simulating outcomes, conditional probability, Bayes' rule, and dependency/independence concepts through hands-on problem-solving and visualization.

    • 📖 Access: Free basic access (premium features available)
    • 🛠️ Hands-on: Yes (interactive problem-solving)
    • 🎯 Topics: Probability estimation, conditional probability, Bayes' rule, modeling
    • [Tags: beginner interactive probability visualization bayes-rule 2025]

  • Pass Your Math - Online Mathematics Courses (Beginner to Intermediate) - Free interactive online basic mathematics, linear algebra, and statistics courses for college and university students. Try courses completely free with no registration required. Self-paced with immediate feedback on mathematical problem-solving.

    • 📖 Access: Fully free, no registration required
    • 🛠️ Hands-on: Yes (interactive problem-solving)
    • 🎯 Topics: Basic mathematics, linear algebra, statistics, college-level
    • [Tags: beginner intermediate interactive free-courses mathematics statistics 2025]

📦 Resource Collections

  • Mathematics for Machine Learning - GitHub Collection (All Levels) - Curated collection of free mathematics resources for ML including textbooks, MIT courses, Khan Academy content, Deep Learning book chapters, and specialized topics like matrix calculus and convex optimization.
    • 📖 Access: Fully open, GitHub
    • [Tags: collection curated-resources all-levels]

🔗 Related Resources

See also:

Cross-reference:

🤝 Contributing

Found a great free mathematics resource for AI/ML? We'd love to add it!

To contribute, use this format:

- [Resource Name](URL) - Clear description highlighting value and what you'll learn. (Difficulty Level)
  - 📖 Access: [access details]
  - [Tags: keyword1 keyword2 keyword3]

Ensure all resources are:

  • ✅ Completely free to access (no payment required)
  • ✅ Openly available (no authentication barriers for core content)
  • ✅ High-quality and educational
  • ✅ Relevant to mathematics for AI/ML
  • ✅ From reputable sources (universities, established platforms, renowned authors)

Last Updated: February 27, 2026 | Total Resources: 44 (+2 new 2026 resources)

Keywords: mathematics-for-machine-learning, linear-algebra, calculus, probability-theory, statistics, optimization, matrix-computation, eigenvalues, gradient-descent, multivariate-calculus, mathematical-foundations, ml-math, 3blue1brown, mit-ocw, khan-academy, imperial-college-london, stanford, pytorch, discrete-math, deeplearning-ai, andrew-ng, simplilearn, matrix-calculus, markov-chains, monte-carlo, tu-delft, convex-optimization, brilliant, stephen-boyd, probability-engineering, statistics-ai-era, uncertainty-quantification, bayesian-inference, meta-statistical-learning, distribution-inference, guvi, ut-austin, harvard, math-for-ai-github, 2025, 2026, pass-your-math, mit-18-05, mit-18-s096, youtube-statistics