AI Agents
6 resourcesAgentic AI with Andrew Ng
Build agentic AI systems with iterative, multi-step workflows. Learn reflection, tool use, planning, and multi-agent patterns from AI pioneer Andrew Ng.
🔗 Enroll for FreeAI Agents for Beginners
Free comprehensive course from Microsoft with 12+ lessons covering AI agent fundamentals. Learn frameworks like AutoGen, Semantic Kernel, and Azure AI Agent Service.
🔗 Start LearningGoogle AI Agents Intensive - Kaggle
5-Day AI Agents Intensive Course with Google on Kaggle. Complete playlist with 5 video sessions covering hands-on intensive training to build advanced AI agent systems with Google's latest tools and frameworks.
🎬 Watch Full PlaylistHugging Face Agents Course
Learn to build AI agents with Hugging Face tools. Comprehensive course covering transformers, agent frameworks, and practical implementations for real-world applications.
🔗 Start LearningAgent Quality Whitepaper - Kaggle
In-depth research whitepaper on AI agent quality metrics and evaluation frameworks. Learn best practices for building and evaluating high-quality AI agents from Kaggle's research community.
🔗 Read WhitepaperPrototype to Production - Kaggle
Comprehensive guide on moving AI agents from prototype to production. Covers deployment strategies, scaling, optimization, monitoring, and maintaining production-ready agent systems.
🔗 Read WhitepaperMachine Learning Foundations
3 resourcesStanford CS229: Machine Learning
Led by Andrew Ng, this graduate-level course provides a broad introduction to machine learning covering supervised learning, unsupervised learning, neural networks, SVMs, reinforcement learning, and applications in robotics and data mining. 20 lectures with comprehensive notes.
🔗 Stanford SEE CourseStanford CS224N: NLP with Deep Learning
Natural Language Processing with Deep Learning by Chris Manning. Covers word embeddings, RNNs, transformers, LLMs, pre-training, post-training, and cutting-edge NLP research.
🔗 Watch Full CourseSupervised Learning with scikit-learn
DataCamp's 4-hour intermediate course covering classification, regression, model evaluation, hyperparameter tuning, and preprocessing pipelines. Learn to predict customer churn, diabetes diagnosis, and more using real-world datasets.
🔗 Start CourseDeep Learning
3 resourcesMIT 6.S191: Introduction to Deep Learning
MIT's introductory deep learning program covering neural networks, CNNs, RNNs, transformers, generative AI, and reinforcement learning. Hands-on labs in Google Colab with 100,000+ global students. Beginner-friendly with calculus prerequisites.
🔗 Watch Full PlaylistDeep Learning in Python Track
DataCamp's comprehensive 4-course track using PyTorch. Build models for image classification, text processing, and learn the Transformers architecture behind ChatGPT. Covers CNNs, RNNs, and pre-trained models.
🔗 Start TrackMIT Hands-on Deep Learning 2024
MIT OpenCourseWare's hands-on deep learning course by Rama Ramakrishnan. Complete lecture videos and notes covering practical deep learning techniques with real-world applications.
🎬 Watch LecturesLarge Language Models
2 resourcesDeveloping Large Language Models
DataCamp's 16-hour track covering LLM concepts, transformer architecture with PyTorch, Hugging Face integration, and building LLM applications with LangChain. Master techniques used in GPT-4 and Llama 3.
🔗 Start TrackStanford CS229 YouTube Lectures
Complete video lecture series from Stanford's CS229 Machine Learning course (Autumn 2018) taught by Andrew Ng. Covers the mathematical theory behind ML algorithms for those aspiring to engage in theoretical research.
🔗 Watch Full CourseReinforcement Learning
1 resourceReinforcement Learning in Python
DataCamp's 12-hour track covering RL fundamentals, Deep Q-Networks, Policy Gradient methods, PPO, and RLHF for training LLMs. Includes hands-on projects in stock trading, robotics, and game AI.
🔗 Start TrackMLOps & Production
1 resourceMLOps Concepts
DataCamp's 2-hour course on deploying ML models to production. Learn feature stores, experiment tracking, CI/CD pipelines, containerization, monitoring, and different MLOps maturity levels.
🔗 Start CourseGoogle AI & Cloud
3 resourcesGoogle AI Essentials
Under 5 hours to learn AI fundamentals, prompt engineering, and responsible AI usage. Created by Google AI experts with hands-on exercises for real workplace scenarios. Earn a Google certificate upon completion.
🔗 Start CourseIntroduction to Vertex AI Studio
Free 1.5-hour Google Cloud course on Gemini multimodal applications, prompt design, model tuning, and the prompt-to-production lifecycle. Includes hands-on labs and skill badge option.
🔗 Start CourseBuild AI Apps with Gemini & Imagen
Free 1.25-hour skill badge course covering image recognition, NLP, image generation using Google's Gemini and Imagen models. Deploy applications on Vertex AI platform. Available in 9 languages.
🔗 Start CourseCS Fundamentals
3 resourcesCS50 - Harvard
Harvard's legendary introduction to computer science. Free course with lectures, problem sets, and certificates.
🔗 Visit CS50 CourseCS50's CS for Business Professionals
Harvard's CS50 variant for business professionals via edX. Covers computational thinking, internet technologies, web development, and cloud computing — designed for tech literacy without deep programming. Free to audit, taught by David J. Malan.
🔗 Visit edX CourseStanford: Transformer Architecture Deep Dive
Advanced Stanford lecture on transformer-based models, covering attention approximation, position embeddings (sinusoidal and RoPE), BERT and derivatives, and key architectural modifications.
🔗 Watch LectureCareer & Development
1 resourceCareer Advice in AI
Expert guidance on building and advancing your career in artificial intelligence. Learn about career paths, skill development, industry trends, and strategies for success in the AI field.
🔗 Watch VideoFree Online Textbooks
11 resourcesUnderstanding Machine Learning
Theory meets algorithms. A comprehensive textbook covering the theoretical foundations of machine learning with rigorous mathematical treatment and practical algorithmic insights.
🔗 Read FreeMathematics for Machine Learning
Linear algebra to calculus made intuitive. Covers the essential mathematical foundations — linear algebra, analytic geometry, matrix decompositions, probability, and optimization — needed for ML.
🔗 Read FreeMathematical Analysis of ML
The theory behind the code. Dive deep into the mathematical analysis that powers machine learning algorithms, from convergence proofs to generalization bounds.
🔗 Read FreeDeep Learning Principles
Neural networks explained clearly. A structured approach to understanding deep learning from fundamental principles, covering architectures, training methods, and modern techniques.
🔗 Read FreeML with Networks
From neurons to backpropagation. Covers neural network fundamentals, learning algorithms, and network architectures with clear explanations of how networks learn from data.
🔗 Read FreeDeep Learning on Graphs
Graph Neural Networks and modern architectures. Explore how deep learning applies to graph-structured data, covering GNNs, message passing, graph transformers, and real-world applications.
🔗 Read FreeAlgorithmic Machine Learning
Complexity and optimization theory. Understand the algorithmic foundations of ML including computational complexity, optimization methods, and efficient learning algorithms.
🔗 Read FreeProbability Theory
Statistical foundations with examples. Build a strong understanding of probability theory essential for machine learning — from distributions and random variables to Bayesian inference.
🔗 Read FreeElementary Probability
Beginner-friendly with real-world applications. An accessible introduction to probability concepts with practical examples, perfect for those starting their ML journey.
🔗 Read FreeAdvanced Data Analysis
Statistical learning for production systems. Advanced methods for data analysis covering regression, classification, model selection, and techniques used in real production ML systems.
🔗 Read FreeML Interview Preparation
Comprehensive resource for preparing for machine learning interviews. Covers key concepts, common questions, and practical tips to ace your ML engineering interviews.
🔗 Read FreeMIT Free Books on AI & ML
10 resourcesFoundations of Machine Learning
By Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. Rigorous mathematical treatment of ML foundations covering PAC learning, Rademacher complexity, boosting, and kernel methods.
🔗 Download FreeUnderstanding Deep Learning
A modern and comprehensive textbook covering neural networks, backpropagation, CNNs, transformers, GANs, diffusion models, and reinforcement learning with interactive notebooks.
🔗 Download FreeAlgorithms for Machine Learning
Covers decision making under uncertainty with practical algorithms. Explores optimization, probabilistic reasoning, sequential decision problems, and multi-agent systems.
🔗 Download FreeReinforcement Learning: An Introduction
By Sutton and Barto. The definitive textbook on reinforcement learning covering multi-armed bandits, MDPs, temporal-difference learning, policy gradient methods, and deep RL.
🔗 Download PDFIntroduction to Machine Learning Systems
Comprehensive guide to building production ML systems. Covers system design, data pipelines, model serving, monitoring, and the full lifecycle of deploying ML at scale.
🔗 Download PDFDeep Learning
By Goodfellow, Bengio, and Courville. The classic deep learning textbook covering linear algebra, probability, numerical computation, neural networks, CNNs, RNNs, and generative models.
🔗 Read OnlineDistributional Reinforcement Learning
MIT Press open access monograph exploring the distributional perspective on RL, where agents learn the full distribution of returns rather than just expected values.
🔗 Download PDFMulti-Agent Reinforcement Learning
Comprehensive resource on MARL covering cooperative, competitive, and mixed multi-agent environments, game theory foundations, and modern deep MARL algorithms.
🔗 Read OnlineAgents in the Long Game of AI
MIT Press open access monograph exploring the role of AI agents in long-term AI development, covering autonomous systems, decision-making, and the future of AI agent architectures.
🔗 Download PDFFairness and Machine Learning
Exploring limitations and opportunities in fairness-aware ML. Covers bias detection, fairness metrics, algorithmic fairness, and building equitable AI systems.
🔗 Read OnlineYouTube Channels
4 resourcesAndrej Karpathy
Former Tesla AI Director and OpenAI co-founder sharing deep dives into neural networks, GPT internals, and building AI from scratch. Essential viewing for understanding how modern AI actually works.
🎬 Visit ChannelStatQuest with Josh Starmer
Statistics and machine learning concepts explained clearly with fun illustrations. Covers everything from basic statistics to neural networks, decision trees, PCA, and more — perfect for building strong ML foundations.
🎬 Visit Channel3Blue1Brown
Beautiful visual explanations of mathematics, linear algebra, calculus, and neural networks. Grant Sanderson's animations make complex mathematical concepts intuitive — a must-watch for understanding the math behind AI.
🎬 Visit ChannelSebastian Raschka
AI researcher and author of "Machine Learning with PyTorch and Scikit-Learn" sharing tutorials on deep learning, LLMs, research paper walkthroughs, and practical machine learning engineering tips.
🎬 Visit ChannelRecommended Books
5 resourcesHands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
By Aurelien Geron. The go-to practical guide for ML engineers covering end-to-end projects with scikit-learn, deep learning with Keras and TensorFlow, CNNs, RNNs, GANs, and reinforcement learning with hands-on code examples.
📖 View on AmazonAn Introduction to Statistical Learning (ISLR)
By James, Witten, Hastie, and Tibshirani. A widely used textbook for learning statistical learning methods including regression, classification, resampling, tree-based methods, SVMs, and unsupervised learning with R and Python labs.
📖 Read Free OnlineThe Hundred-Page Machine Learning Book
By Andriy Burkov. A concise yet comprehensive overview of machine learning covering supervised and unsupervised learning, neural networks, and best practices — perfect for quick reference and exam preparation.
📖 Visit Official SiteMachine Learning Yearning
By Andrew Ng. A practical guide focused on structuring ML projects, diagnosing errors, and making strategic decisions. Learn how to set up dev/test sets, handle bias and variance, and build effective ML pipelines.
📖 Download Free PDFPattern Recognition and Machine Learning
By Christopher M. Bishop. A comprehensive textbook covering probability distributions, linear models, neural networks, kernel methods, graphical models, and approximate inference — the gold standard for ML theory.
📖 Read Free (Microsoft Research)More Resources Coming Soon
We're constantly discovering and curating new free learning resources. Check back regularly for updates on AI tools, programming frameworks, and educational content.