FREE ML Courses
Curated collection of machine learning courses from top universities. All courses are freely available online.
60+
Courses
0
Universities
100%
Free
Massachusetts Institute of Technology
MIT 6.036: Introduction to Machine Learning
Fundamental machine learning algorithms including supervised and unsupervised learning, regression, classification, and clustering with practical implementation.
MIT 6.S191: Introduction to Deep Learning
A comprehensive introduction to deep learning methods with applications in computer vision, natural language processing, and more.
MIT 6.S087: Foundation Models and Generative AI
Future of AI - from foundation models to applications in both science and business: ChatGPT, Copilot, CLIP, Dall-E, Stable-Diffusion, AlphaFold, Self-driving cars.
MIT 9.520: Statistical Learning Theory and Applications
Theoretical foundations and recent advances of machine learning including statistical learning theory, regularization, kernel methods, and optimization.
MIT 6.878: Machine Learning in Genomics
Foundations and frontiers of machine learning, statistical, and algorithmic techniques for understanding the human genome.
MIT 6.S897: Machine Learning for Healthcare
Applied machine learning in healthcare, covering clinical prediction, medical imaging analysis, and data challenges with real-world case studies.
MIT: 6.874: Deep Learning in the Life Sciences
Introduces the foundations and state-of-the-art machine learning challenges in genomics and the life sciences more broadly.
MIT: 6.S192: Deep Learning for Art, Aesthetics, and Creativity
Explores the intersection of deep learning and the arts, focusing on cutting-edge creative applications and cultural implications.
Stanford University
CS229: Machine Learning
One of the most comprehensive machine learning courses available. Covers supervised learning, unsupervised learning, and best practices.
CS231n: Deep Learning for Computer Vision
Deep dive into computer vision and convolutional neural networks, covering image classification, object detection, and modern CNN architectures.
CS224n: Natural Language Processing with Deep Learning
Modern NLP techniques using deep learning, including word embeddings, RNNs, Transformers, and large language models.
CS230: Deep Learning
Practical deep learning course covering neural networks, CNNs, RNNs, LSTM, Adam, Dropout, and deep learning project methodology.
CS234: Reinforcement Learning
Comprehensive reinforcement learning course covering Markov decision processes, policy gradients, and Q-learning.
CS236: Deep Generative Models
Advanced course on generative models including speech, CV, NLP, RL, VAEs, GANs, autoregressive models, and diffusion models.
CS336: Language Modeling from Scratch
This course for a comprehensive understanding of language models by walking them through the entire process of developing their own.
CS221: Artificial Intelligence. Principles and Techniques
Foundational principles of AI systems. Specific topics include machine learning, search, Markov decision processes, constraint satisfaction, and logic.
CS228: Probabilistic Graphical Models
This course for a comprehensive understanding of language models by walking them through the entire process of developing their own.
University of California, Berkeley
UC Berkeley and UW 590C: Full Stack Deep Learning
Practical course on deploying deep learning systems in production, covering MLOps, monitoring, and scaling ML applications.
CS 294: Deep Unsupervised Learning
Theoretical foundations of deep generative models and self-supervised learning and their newly enabled applications in images, audio, and text analyses.
CS 285: Deep Reinforcement Learning
Advanced reinforcement learning course covering policy gradients, actor-critic methods, model-based RL, and meta-learning.
CS 188: Introduction to Artificial Intelligence
Foundational course that covers search algorithms, game theory, constraint satisfaction, machine learning, and artificial intelligence ethics.
CS 189: Introduction to Machine Learning
Theoretical foundations, algorithms, and applications of machine learning, combining mathematical rigor with practical experience.
CS 288: Natural Language Processing
Overview of the natural language processing and deeper dive into recent advances, particularly large transfomer models such as GPT.
CS 182: Designing, Visualizing and Understanding DNNs
An advanced course that covers the ground from principles to designing, visualization and understanding of deep neural networks.
CSC 08: Foundations of Data Science
Foundational course that combines concepts of inferential thinking, computational thinking, and topics of real-world relevance.
Carnegie Mellon University
CMU 11-785: Introduction to Deep Learning
Comprehensive deep learning course with fundamentals and hands-on assignments covering neural networks and attention mechanisms.
CMU 11-611: Natural Language Processing
Comprehensive natural language processing course covering traditional and modern approaches to language understanding and generation.
CMU 11-711: Advanced Natural Language Processing
An introductory graduate-level course on natural language processing aimed at students who are interested in doing cutting-edge research in the field.
CMU 11-737: Multilingual Natural Language Processing
An advanced graduate-level course that covers multilingual or cross-lingual methods, linguistically informed NLP models, and bootstrapping systems.
CMU 11-747: Neural Networks for Natural Language Processing
An advanced course that demonstrates neural networks application to natural language problems with different techniques for models creation.
CMU 11-891: Neural Code Generation
An advanced course on modeling and synthesizing programs using deep-learning methods, with an emphasis on neural language models.
CMU 11-777: MultiModal Machine Learning
A vibrant multi-disciplinary research field that integrates and models multiple communicative modalities, including linguistic, acoustic, and visual messages.
CMU 10-701: Introduction to Machine Learning
Comprehensive deep learning course with fundamentals and hands-on assignments covering neural networks and attention mechanisms.
New York University
CSCI 0472: Artificial Intelligence
Modern course by Alfredo Canziani on knowledge-based and learning-based artificial intelligence for natural language processing.
DSGA 1008: Deep Learning
World-renowned deep learning course by Yann LeCun and Alfredo Canziani, covering theoretical foundations and practical applications of deep neural networks.
University of Chicago
CMSC 35300: Mathematical Foundations of Machine Learning
An introduction to key mathematical concepts at the heart of machine learning by Rebecca Willett, focuses on matrix methods and statistical models.
CMSC 35400: Machine Learning (STAT37710)
A systematic view of a range of contemporary machine learning algorithms including mixture models, deep learning, and nonparametric methods.