268 resources
AI
Foundations through to applied, model-building work — from the theory in the standard textbooks to landmark papers, framework docs, and full lecture series.
268 resources
Documents 211
Deep Learning
Comprehensive free online textbook covering the mathematical foundations and core methods of deep learning.
Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Dive into Deep Learning
Interactive open-source book teaching deep learning concepts alongside runnable code in multiple frameworks.
Aston Zhang, Zachary Lipton, Mu Li, Alexander Smola
Neural Networks and Deep Learning
Free online book building neural network intuition from first principles, including backpropagation from scratch.
Michael Nielsen
The Elements of Statistical Learning
Graduate-level textbook on statistical learning theory, regression, classification, and model selection.
Trevor Hastie, Robert Tibshirani, Jerome Friedman
An Introduction to Statistical Learning
Accessible textbook introducing statistical learning methods with applied examples and exercises.
Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani
Mathematics for Machine Learning
Free textbook covering linear algebra, calculus, probability, and optimization needed for machine learning.
Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong
Probabilistic Machine Learning: An Introduction
Free textbook draft covering probabilistic approaches to machine learning fundamentals.
Kevin Murphy
Probabilistic Machine Learning: Advanced Topics
Companion volume covering advanced probabilistic modeling and inference topics in machine learning.
Kevin Murphy
Pattern Recognition and Machine Learning
Classic textbook on pattern recognition covering Bayesian methods, graphical models, and neural networks.
Christopher Bishop / Microsoft Research
Convex Optimization
Free textbook on convex optimization theory and algorithms underlying many ML training methods.
Stephen Boyd and Lieven Vandenberghe
The Matrix Cookbook
Reference document of matrix identities and derivatives useful for ML math derivations.
Kaare Brandt Petersen and Michael Syskind Pedersen
CS229: Machine Learning Course Notes
Stanford's foundational machine learning course notes covering supervised, unsupervised, and reinforcement learning.
Stanford University
CS231n: Convolutional Neural Networks for Visual Recognition
Stanford course notes on convolutional neural networks and deep learning for computer vision.
Stanford University
CS224n: Natural Language Processing with Deep Learning
Stanford course page covering deep learning approaches to natural language processing.
Stanford University
CS230 Deep Learning Cheatsheets
Condensed reference cheatsheets summarizing key deep learning concepts from Stanford's CS230 course.
Shervine and Afshine Amidi / Stanford University
6.036 Introduction to Machine Learning
MIT's free introductory machine learning course materials including notes and problem sets.
MIT OpenCourseWare
18.06 Linear Algebra
MIT's classic linear algebra course materials, foundational math for machine learning.
MIT OpenCourseWare
CS189: Introduction to Machine Learning
Berkeley's introductory machine learning course page with lecture notes and readings.
UC Berkeley
10-701: Introduction to Machine Learning
CMU's graduate-level introductory machine learning course materials.
Carnegie Mellon University
11-785: Introduction to Deep Learning
CMU's deep learning course site covering neural network architectures and training techniques.
Carnegie Mellon University
PyTorch Tutorials
Official PyTorch tutorials covering tensors, autograd, and building neural networks.
PyTorch / Meta AI
PyTorch Documentation
Official reference documentation for the PyTorch deep learning framework's API.
PyTorch / Meta AI
TensorFlow Guide
Official TensorFlow guide explaining core concepts, APIs, and best practices.
TensorFlow Tutorials
Official step-by-step tutorials for building and training models with TensorFlow.
JAX Documentation
Official documentation for JAX, a framework for high-performance numerical computing and ML research.
Google DeepMind
scikit-learn User Guide
Official comprehensive guide to classical machine learning algorithms implemented in scikit-learn.
scikit-learn developers
Hugging Face NLP Course
Free course covering transformers and natural language processing using the Hugging Face ecosystem.
Hugging Face
fastai Documentation
Official documentation for the fastai deep learning library built on PyTorch.
fast.ai
Machine Learning Crash Course
Google's free self-study guide introducing core machine learning concepts and TensorFlow exercises.
Machine Learning Glossary
Google's reference glossary defining common machine learning and deep learning terminology.
Spinning Up in Deep RL
OpenAI's educational resource introducing deep reinforcement learning theory and implementations.
OpenAI
Intro to Machine Learning
Kaggle Learn micro-course introducing core machine learning modeling concepts with hands-on exercises.
Kaggle
Intermediate Machine Learning
Kaggle Learn micro-course on handling missing data, categorical variables, and pipelines.
Kaggle
Intro to Deep Learning
Kaggle Learn micro-course covering neural network fundamentals using Keras and TensorFlow.
Kaggle
Feature Engineering
Kaggle Learn micro-course on creating and selecting features to improve model performance.
Kaggle
Data Cleaning
Kaggle Learn micro-course teaching techniques for handling missing values and inconsistent data.
Kaggle
Pandas
Kaggle Learn micro-course teaching data manipulation with the pandas library for ML workflows.
Kaggle
Machine Learning Explainability
Kaggle Learn micro-course on techniques for interpreting and explaining machine learning model predictions.
Kaggle
The Building Blocks of Interpretability
Interactive article combining feature visualization and attribution to interpret neural networks.
Distill.pub
Attention and Augmented Recurrent Neural Networks
Visual explainer covering attention mechanisms and memory-augmented recurrent neural network architectures.
Distill.pub
Why Momentum Really Works
Interactive article explaining the mathematics and intuition behind momentum-based optimization.
Distill.pub
A Visual Exploration of Gaussian Processes
Interactive article building intuition for Gaussian processes through visualizations.
Distill.pub
Exploring Neural Networks with Activation Atlases
Article visualizing what neural network layers learn using activation atlas techniques.
Distill.pub
A Gentle Introduction to Graph Neural Networks
Interactive introduction explaining how graph neural networks represent and learn from graph data.
Distill.pub
Feature Visualization
Article explaining how neural networks build up their understanding of images through visualization.
Distill.pub
Understanding LSTM Networks
Widely-cited illustrated explanation of how long short-term memory networks function.
Christopher Olah (colah's blog)
Neural Networks, Manifolds, and Topology
Essay exploring neural networks through the lens of topology and manifold geometry.
Christopher Olah (colah's blog)
Conv Nets: A Modular Perspective
Explanatory post framing convolutional networks as compositions of modular operations.
Christopher Olah (colah's blog)
Deep Learning, NLP, and Representations
Essay on how deep learning models learn distributed representations for language.
Christopher Olah (colah's blog)
Calculus on Computational Graphs: Backpropagation
Clear explanation of backpropagation using computational graphs and the chain rule.
Christopher Olah (colah's blog)
Visualizing MNIST
Essay exploring dimensionality reduction techniques applied to the MNIST digit dataset.
Christopher Olah (colah's blog)
Attention? Attention!
In-depth blog post surveying attention mechanisms used across deep learning architectures.
Lilian Weng (Lil'Log)
From GAN to WGAN
Detailed post explaining the mathematics of generative adversarial networks and Wasserstein GANs.
Lilian Weng (Lil'Log)
A (Long) Peek into Reinforcement Learning
Comprehensive blog post surveying key concepts and algorithms in reinforcement learning.
Lilian Weng (Lil'Log)
Self-Supervised Representation Learning
Blog post surveying self-supervised learning methods for images, text, and other modalities.
Lilian Weng (Lil'Log)
What are Diffusion Models?
Detailed technical post explaining the mathematics behind diffusion-based generative models.
Lilian Weng (Lil'Log)
Neural Architecture Search
Blog post surveying methods for automatically searching neural network architectures.
Lilian Weng (Lil'Log)
The Illustrated Transformer
Widely-referenced visual explanation of the transformer architecture underlying modern language models.
Jay Alammar
The Illustrated BERT, ELMo, and co.
Visual explainer of contextual word embedding models including BERT and ELMo.
Jay Alammar
Visualizing A Neural Machine Translation Model
Illustrated walkthrough of sequence-to-sequence models with attention for machine translation.
Jay Alammar
A Visual and Interactive Guide to the Basics of Neural Networks
Beginner-friendly illustrated introduction to how neural networks compute and learn.
Jay Alammar
The Illustrated Word2vec
Visual explanation of how word2vec learns dense word embeddings from text.
Jay Alammar
How GPT3 Works - Visualizations and Animations
Illustrated explainer of how the GPT-3 language model processes and generates text.
Jay Alammar
Principal Component Analysis in 3 Simple Steps
Step-by-step tutorial explaining the mathematics and implementation of PCA.
Sebastian Raschka
Naive Bayes and Text Classification
Article explaining the theory behind naive Bayes classifiers applied to text data.
Sebastian Raschka
Linear Discriminant Analysis
Tutorial explaining linear discriminant analysis for dimensionality reduction and classification.
Sebastian Raschka
The Unreasonable Effectiveness of Recurrent Neural Networks
Influential essay demonstrating character-level language modeling with recurrent neural networks.
Andrej Karpathy
A Recipe for Training Neural Networks
Practical essay outlining a systematic recipe for debugging and training neural networks.
Andrej Karpathy
Yes You Should Understand Backprop
Essay arguing why practitioners should understand backpropagation's mechanics rather than treat it as a black box.
Andrej Karpathy
CS231n Notes: Neural Networks Part 1
Course notes covering neurons, activation functions, and neural network architecture basics.
Stanford University
CS231n Notes: Neural Networks Part 2
Course notes covering data preprocessing, weight initialization, and regularization for neural networks.
Stanford University
CS231n Notes: Neural Networks Part 3
Course notes covering gradient checking, training dynamics, and evaluation of neural networks.
Stanford University
CS231n Notes: Optimization
Course notes explaining gradient descent and optimization techniques for training neural networks.
Stanford University
CS231n Notes: Convolutional Networks
Course notes explaining convolutional layer architecture and design for visual recognition.
Stanford University
The Hugging Face NLP Course – Chapter 1: Transformer Models
Introduces transformer architectures and the NLP pipeline for beginners.
Hugging Face
The Hugging Face NLP Course – Chapter 2: Using Transformers
Explains tokenizers, models, and the pipeline API in the Transformers library.
Hugging Face
The Hugging Face NLP Course – Chapter 3: Fine-Tuning a Model
Walks through fine-tuning a pretrained transformer with the Trainer API.
Hugging Face
The Hugging Face NLP Course – Chapter 4: Sharing Models and Tokenizers
Covers the Model Hub and how to publish trained models and tokenizers.
Hugging Face
The Hugging Face NLP Course – Chapter 5: The Datasets Library
Teaches loading, processing, and slicing datasets for NLP tasks.
Hugging Face
The Hugging Face NLP Course – Chapter 6: The Tokenizers Library
Details training and customizing fast tokenizers for transformer models.
Hugging Face
The Hugging Face NLP Course – Chapter 7: Main NLP Tasks
Applies transformers to token classification, QA, translation, and summarization.
Hugging Face
The Hugging Face NLP Course – Chapter 8: How to Ask for Help
Guides debugging training pipelines and getting help from the community.
Hugging Face
Hugging Face Deep RL Course – Unit 1: Introduction to Deep RL
Introduces reinforcement learning fundamentals through hands-on agents.
Hugging Face
Hugging Face Deep RL Course – Unit 2: Q-Learning
Explains tabular Q-learning and value-based reinforcement learning.
Hugging Face
Hugging Face Deep RL Course – Unit 4: Policy Gradient Methods
Covers policy-gradient algorithms like REINFORCE for continuous control.
Hugging Face
Hugging Face Deep RL Course – Unit 6: Actor-Critic Methods
Explains Advantage Actor-Critic (A2C) methods with Stable-Baselines3.
Hugging Face
Hugging Face Deep RL Course – Unit 8: Proximal Policy Optimization
Details the PPO algorithm and its implementation from scratch.
Hugging Face
Hugging Face Diffusion Models Course – Unit 1
Introduces diffusion model theory and training with the diffusers library.
Hugging Face
Hugging Face Computer Vision Course – Welcome Unit
Free course covering CNNs, vision transformers, and multimodal vision models.
Hugging Face
Hugging Face Agents Course – Unit 0: Introduction
Introduces building LLM-powered agents and tool-use workflows.
Hugging Face
Transformers Library Documentation
Reference documentation for the Transformers library covering models and pipelines.
Hugging Face
PEFT Library Documentation
Documents parameter-efficient fine-tuning methods including LoRA for LLMs.
Hugging Face
Diffusers Library Documentation
Reference docs for training and running diffusion models for image generation.
Hugging Face
Tokenizers Library Documentation
Documents fast tokenizer training and usage for NLP pipelines.
Hugging Face
Accelerate Library Documentation
Explains distributed and mixed-precision training for PyTorch models.
Hugging Face
Datasets Library Documentation
Reference documentation for loading and processing machine learning datasets.
Hugging Face
CS231n: Deep Learning for Computer Vision
Stanford's course site on convolutional neural networks for visual recognition.
Stanford University
CS25: Transformers United (Course Site)
Stanford seminar course site exploring transformer architectures across domains.
Stanford University
Spinning Up: Part 1 - Key Concepts in RL
Introduces core reinforcement learning terminology and notation.
OpenAI
Spinning Up: Part 2 - Kinds of RL Algorithms
Surveys the taxonomy of model-free and model-based RL algorithms.
OpenAI
Spinning Up: Vanilla Policy Gradient
Documents the vanilla policy gradient algorithm with implementation details.
OpenAI
Spinning Up: Proximal Policy Optimization
Explains the PPO algorithm as implemented in the Spinning Up library.
OpenAI
Spinning Up: Trust Region Policy Optimization
Documents the TRPO algorithm for stable policy updates.
OpenAI
Spinning Up: Deep Deterministic Policy Gradient
Documents DDPG, an off-policy algorithm for continuous action spaces.
OpenAI
Spinning Up: Twin Delayed DDPG
Explains TD3, an improvement over DDPG for continuous control tasks.
OpenAI
Spinning Up: Soft Actor-Critic
Documents the SAC algorithm combining maximum entropy RL with actor-critic methods.
OpenAI
LangChain Documentation: Introduction
Official entry point to LangChain's Python framework for building LLM applications.
LangChain
LangChain Documentation: Tutorials
Step-by-step tutorials for building chatbots, RAG apps, and agents with LangChain.
LangChain
LangChain Documentation: Concepts
Explains core LangChain concepts such as chains, memory, and retrievers.
LangChain
LlamaIndex Documentation
Official documentation for the LlamaIndex data framework for LLM applications.
LlamaIndex
LlamaIndex: High-Level Concepts
Explains indexing, retrieval, and query engines used in LlamaIndex.
LlamaIndex
vLLM Documentation
Official documentation for the vLLM high-throughput LLM inference engine.
vLLM Project
vLLM Quickstart Guide
Walks through installing and running vLLM for fast LLM serving.
vLLM Project
Attention Is All You Need
The landmark paper introducing the transformer architecture.
Google Brain / Google Research
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Introduces BERT, a bidirectional transformer pretraining approach for NLP.
Google AI Language
Language Models are Few-Shot Learners (GPT-3)
Introduces GPT-3 and demonstrates few-shot learning at scale.
OpenAI
Deep Residual Learning for Image Recognition (ResNet)
Introduces residual connections enabling very deep convolutional networks.
Microsoft Research
Very Deep Convolutional Networks for Large-Scale Image Recognition (VGG)
Introduces the VGG family of deep convolutional network architectures.
University of Oxford
Going Deeper with Convolutions (GoogLeNet/Inception)
Introduces the Inception architecture for efficient deep image classification.
An Image is Worth 16x16 Words: Vision Transformer (ViT)
Introduces applying pure transformer architectures to image classification.
Google Research
Generative Adversarial Networks
The original paper introducing the GAN framework for generative modeling.
Ian Goodfellow et al.
Denoising Diffusion Probabilistic Models
Introduces DDPMs, the foundation for modern image diffusion models.
UC Berkeley
High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion)
Introduces latent diffusion, the technique underlying Stable Diffusion.
LMU Munich / Runway
Learning Transferable Visual Models From Natural Language Supervision (CLIP)
Introduces CLIP, a model linking images and text via contrastive pretraining.
OpenAI
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5)
Introduces T5 and a unified text-to-text framework for NLP transfer learning.
Google Research
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Presents an optimized BERT pretraining recipe improving downstream performance.
Facebook AI Research
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Introduces XLNet, an autoregressive pretraining method outperforming BERT.
Google AI / CMU
ELECTRA: Pre-training Text Encoders as Discriminators
Introduces a sample-efficient pretraining task using replaced token detection.
Stanford University / Google Brain
Efficient Estimation of Word Representations in Vector Space (Word2Vec)
Introduces word2vec, foundational word embedding models for NLP.
Deep Contextualized Word Representations (ELMo)
Introduces ELMo, contextual word embeddings derived from a bidirectional LSTM.
Allen Institute for AI
Sequence to Sequence Learning with Neural Networks
Introduces the seq2seq framework for neural machine translation.
Neural Machine Translation by Jointly Learning to Align and Translate
Introduces the attention mechanism for neural machine translation.
University of Montreal
Training Language Models to Follow Instructions with Human Feedback (InstructGPT)
Describes RLHF fine-tuning to align language models with user intent.
OpenAI
LLaMA: Open and Efficient Foundation Language Models
Introduces Meta's LLaMA family of open foundation language models.
Meta AI
Llama 2: Open Foundation and Fine-Tuned Chat Models
Describes the Llama 2 pretraining and RLHF fine-tuning process.
Meta AI
PaLM: Scaling Language Modeling with Pathways
Describes the 540-billion-parameter PaLM language model and its capabilities.
Google Research
Training Compute-Optimal Large Language Models (Chinchilla)
Establishes scaling laws for compute-optimal LLM training.
Google DeepMind
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Shows that intermediate reasoning steps improve LLM problem-solving.
Google Research
Deep Reinforcement Learning from Human Preferences
Introduces learning reward functions from human preference comparisons.
OpenAI / DeepMind
LoRA: Low-Rank Adaptation of Large Language Models
Introduces LoRA, a parameter-efficient method for fine-tuning large models.
Microsoft Research
Switch Transformers: Scaling to Trillion Parameter Models
Introduces sparse mixture-of-experts scaling for transformer models.
Google Research
Proximal Policy Optimization Algorithms
Introduces PPO, a widely used policy-gradient reinforcement learning algorithm.
OpenAI
Mastering Chess and Shogi by Self-Play with a General RL Algorithm (AlphaZero)
Describes AlphaZero, which mastered chess, shogi, and Go via self-play.
DeepMind
Playing Atari with Deep Reinforcement Learning (DQN)
Introduces the Deep Q-Network combining Q-learning with deep neural networks.
DeepMind
Trust Region Policy Optimization
Introduces TRPO, a stable policy optimization method for reinforcement learning.
UC Berkeley / OpenAI
Continuous Control with Deep Reinforcement Learning (DDPG)
Introduces DDPG for continuous action-space reinforcement learning.
DeepMind
Soft Actor-Critic: Off-Policy Maximum Entropy Deep RL
Introduces SAC, combining entropy maximization with off-policy actor-critic learning.
UC Berkeley
Asynchronous Methods for Deep Reinforcement Learning (A3C)
Introduces asynchronous actor-critic methods for parallel RL training.
DeepMind
You Only Look Once: Unified, Real-Time Object Detection (YOLO)
Introduces YOLO, a single-pass real-time object detection architecture.
University of Washington
Faster R-CNN: Towards Real-Time Object Detection
Introduces the region proposal network underlying modern object detectors.
Microsoft Research
U-Net: Convolutional Networks for Biomedical Image Segmentation
Introduces the U-Net architecture widely used for image segmentation.
University of Freiburg
Mask R-CNN
Extends Faster R-CNN to perform pixel-level instance segmentation.
Facebook AI Research
EfficientNet: Rethinking Model Scaling for CNNs
Introduces compound scaling for building efficient convolutional networks.
Google Research
Densely Connected Convolutional Networks (DenseNet)
Introduces DenseNet, connecting each layer to every other layer feed-forward.
Cornell University / Facebook AI Research
MobileNets: Efficient CNNs for Mobile Vision Applications
Introduces lightweight convolutional architectures for mobile and embedded vision.
A Style-Based Generator Architecture for GANs (StyleGAN)
Introduces the StyleGAN architecture for high-quality controllable image synthesis.
NVIDIA
Segment Anything
Introduces the Segment Anything Model and dataset for promptable image segmentation.
Meta AI Research
Zero-Shot Text-to-Image Generation (DALL-E)
Describes the original DALL-E model for generating images from text prompts.
OpenAI
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Introduces RAG, combining retrieval with generation for knowledge-grounded NLP.
Facebook AI Research
Scaling Laws for Neural Language Models
Establishes empirical scaling laws relating model size, data, and compute.
OpenAI
GPT-4 Technical Report
Technical report describing GPT-4's capabilities, training, and evaluation.
OpenAI
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Introduces Mamba, a state-space model alternative to transformers for sequences.
Carnegie Mellon University / Princeton University
FlashAttention: Fast and Memory-Efficient Exact Attention
Introduces an IO-aware exact attention algorithm speeding up transformer training.
Stanford University
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Introduces DPO, a simpler alternative to RLHF for aligning language models.
Stanford University
Constitutional AI: Harmlessness from AI Feedback
Describes training harmless AI assistants using AI-generated feedback and a constitution.
Anthropic
Self-Instruct: Aligning Language Models with Self-Generated Instructions
Introduces a method for bootstrapping instruction-tuning data from a language model itself.
University of Washington
ReAct: Synergizing Reasoning and Acting in Language Models
Introduces interleaving reasoning traces with actions for language model agents.
Princeton University / Google Research
Toolformer: Language Models Can Teach Themselves to Use Tools
Shows language models learning to call external tools via self-supervision.
Meta AI Research
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Introduces a framework for exploring multiple reasoning paths in LLMs.
Princeton University / Google DeepMind
Mistral 7B
Technical report introducing the efficient open-weight Mistral 7B language model.
Mistral AI
Gemini: A Family of Highly Capable Multimodal Models
Technical report describing Google's Gemini family of multimodal models.
Google DeepMind
Denoising Diffusion Implicit Models (DDIM)
Introduces a faster, non-Markovian sampling procedure for diffusion models.
Stanford University
Batch Normalization: Accelerating Deep Network Training
Introduces batch normalization to stabilize and accelerate deep network training.
Image-to-Image Translation with Conditional Adversarial Networks (pix2pix)
Introduces a conditional GAN framework for general-purpose image translation.
UC Berkeley
Papers with Code: Language Modelling
Curated hub of language modeling benchmarks, papers, and leaderboards.
Papers with Code
Papers with Code: Image Classification
Curated hub of image classification benchmarks, datasets, and state-of-the-art papers.
Papers with Code
Papers with Code: Object Detection
Curated hub of object detection benchmarks, methods, and papers.
Papers with Code
Papers with Code: Transformer Method Page
Overview page collecting papers and models built on the transformer architecture.
Papers with Code
Papers with Code: BERT Method Page
Overview page collecting papers, models, and usages of BERT.
Papers with Code
Constitutional AI: Harmlessness from AI Feedback (Research Post)
Anthropic's public research post explaining its Constitutional AI method.
Anthropic
Core Views on AI Safety
Anthropic's public explanation of its approach and philosophy toward AI safety.
Anthropic
Introducing ChatGPT
OpenAI's announcement post introducing the ChatGPT conversational model.
OpenAI
CLIP: Connecting Text and Images
OpenAI's blog post introducing the CLIP model linking vision and language.
OpenAI
DALL·E 2
OpenAI's announcement post introducing the DALL·E 2 image generation model.
OpenAI
Large Language Model Llama Meta AI
Meta's blog post announcing the LLaMA family of foundation language models.
Meta AI
Segment Anything: A Foundation Model for Image Segmentation
Meta's blog post introducing the Segment Anything Model and dataset.
Meta AI
Made With ML
Free end-to-end course covering ML system design, MLOps, and production best practices.
Goku Mohandas / Anyscale
MLOps: Continuous Delivery and Automation Pipelines in Machine Learning
Google's architecture guide explaining CI/CD and automation practices for ML systems.
Google Cloud
Model Management and Deployment (Azure Machine Learning)
Microsoft's documentation on managing, versioning, and deploying ML models on Azure.
Microsoft Azure
Vertex AI: Introduction to MLOps
Google Cloud's introductory documentation on applying MLOps practices with Vertex AI.
Google Cloud
Rules of Machine Learning: Best Practices for ML Engineering
Google's 43 practical rules distilled from real-world production ML engineering experience.
Google Developers (Martin Zinkevich)
Statistics and Probability
Free full-length course covering descriptive statistics, probability, and inference.
Khan Academy
Seeing Theory
Interactive visual introduction to probability and statistics built with D3.js.
Brown University (Daniel Kunin)
MLflow Documentation
Official documentation for tracking, packaging, and deploying ML experiments with MLflow.
MLflow (Linux Foundation)
Weights & Biases Developer Guide
Official docs for experiment tracking, evaluation, and model observability with W&B.
Weights & Biases
DVC Documentation
Official documentation for Data Version Control, a Git-based tool for ML data and pipelines.
Iterative (DVC)
Get Started with DVC
Hands-on quick-start guide to versioning data and building ML pipelines with DVC.
Iterative (DVC)
Google AI Principles and Responsible AI Practices
Google's public framework and practices for building AI responsibly and safely.
Google AI
Partnership on AI Resource Library
Collection of papers, reports, and tools on responsible and ethical AI development.
Partnership on AI
OpenAI Research
OpenAI's index of research publications, papers, and technical reports.
OpenAI
OpenAI Blog / News
OpenAI's official news and announcements covering research and product updates.
OpenAI
Anthropic Research
Anthropic's index of publications on AI safety, alignment, and interpretability research.
Anthropic
Anthropic News
Anthropic's official announcements covering models, research, and policy updates.
Anthropic
Google Research Blog
Google Research's blog covering the latest work across AI and computer science.
Google Research
Meta AI Blog
Meta's official blog covering AI research announcements and model releases.
Meta AI
Practical Deep Learning for Coders
Free applied deep learning course with videos, an interactive book, and notebooks.
fast.ai (Jeremy Howard)
Hugging Face Deep RL Course
Free course teaching deep reinforcement learning theory and hands-on implementation.
Hugging Face
Google AI Education
Curated hub of Google's free AI learning resources for students and professionals.
Google AI
AWS Well-Architected Machine Learning Lens
AWS guidance for designing and operating reliable, well-architected ML workloads.
Amazon Web Services
Google Cloud MLOps Whitepaper: Practitioners Guide
Google's whitepaper detailing MLOps maturity levels and practical implementation guidance.
Google Cloud
Azure Machine Learning Documentation
Full documentation hub for building, training, and deploying models on Azure ML.
Microsoft Azure
Videos 57
Neural Networks
Visual, intuition-first playlist explaining how neural networks and backpropagation actually work.
3Blue1Brown
Machine Learning
Clearly explained walkthroughs of core machine learning algorithms, from trees to boosting.
StatQuest with Josh Starmer
Neural Networks / Deep Learning
Step-by-step explanations of neural network fundamentals through convolutional networks.
StatQuest with Josh Starmer
Logistic Regression
Dedicated playlist breaking down logistic regression theory and interpretation step by step.
StatQuest with Josh Starmer
Neural Networks: Zero to Hero
Karpathy builds neural networks and GPT-like models from scratch in code, lecture by lecture.
Andrej Karpathy
Andrej Karpathy (channel)
Former Tesla and OpenAI researcher's channel with deep, code-first explanations of AI systems.
Andrej Karpathy
Two Minute Papers (channel)
Short, accessible summaries of the latest AI and computer graphics research papers.
Two Minute Papers
Yannic Kilcher (channel)
In-depth video breakdowns of machine learning research papers and AI community news.
Yannic Kilcher
sentdex (channel)
Harrison Kinsley's channel covering practical Python-based machine learning and deep learning tutorials.
sentdex
Neural Networks from Scratch in Python
Builds a neural network library from scratch in Python without deep learning frameworks.
sentdex
Machine Learning with Python
Practical, code-driven introduction to machine learning algorithms implemented in Python.
sentdex
Computerphile (channel)
Brady Haran's computer science channel with frequent explainers on AI and neural networks.
Computerphile
CodeEmporium (channel)
AI-focused channel explaining transformers, NLP, and deep learning concepts with visuals and code.
CodeEmporium
DeepLearning.AI (channel)
Andrew Ng's organization shares lectures, course previews, and AI career guidance videos.
DeepLearning.AI
Google DeepMind (channel)
Official channel with research talks, documentaries, and explainers from Google DeepMind.
Google DeepMind
Deep Learning Lecture Series 2021
Graduate-level deep learning lectures co-produced by DeepMind and University College London.
DeepMind x UCL
OpenAI (channel)
Official OpenAI channel featuring product demos, research talks, and model announcements.
OpenAI
MIT 6.S191: Introduction to Deep Learning
MIT's official introductory deep learning course lectures, covering theory and applications.
MIT
CS224N: NLP with Deep Learning (Winter 2021)
Stanford's graduate course on natural language processing using deep learning methods.
Stanford Online
CS229: Machine Learning Full Course (Autumn 2018)
Stanford's classic graduate machine learning course covering theory and mathematical foundations.
Stanford Online (Andrew Ng)
CS230: Deep Learning (Autumn 2018)
Stanford's deep learning course covering CNNs, RNNs, and real-world case studies.
Stanford Online (Andrew Ng)
CS25: Transformers United (Lecture Videos)
Stanford seminar series with guest researchers on transformer architectures and applications.
Stanford Online
Deep Learning Course
NYU graduate deep learning course taught by Turing Award winner Yann LeCun.
Yann LeCun & Alfredo Canziani (NYU)
Lex Fridman (channel)
Long-form interviews and lectures with AI researchers, scientists, and technology leaders.
Lex Fridman
deeplizard (channel)
Structured video courses on deep learning fundamentals, PyTorch, Keras, and reinforcement learning.
deeplizard
Machine Learning Street Talk (channel)
In-depth discussions and interviews with AI researchers about cutting-edge machine learning ideas.
Machine Learning Street Talk
Robert Miles AI Safety (channel)
Explainer videos on AI safety, alignment, and the risks of advanced artificial intelligence.
Robert Miles
Krish Naik (channel)
Extensive tutorial library covering machine learning, deep learning, and data science in Python.
Krish Naik
codebasics (channel)
Dhaval Patel's channel teaching programming, data analysis, and machine learning practically.
codebasics
Machine Learning Tutorial Python
Beginner-friendly Python machine learning tutorial series covering core algorithms step by step.
codebasics
Nicholas Renotte (channel)
Project-based tutorials on deep learning, computer vision, and applied machine learning.
Nicholas Renotte
Weights & Biases (channel)
MLOps and experiment-tracking tutorials plus talks from machine learning practitioners.
Weights & Biases
Hugging Face (channel)
Tutorials and talks on transformers, NLP, and open-source machine learning tools.
Hugging Face
TensorFlow (channel)
Official Google channel with tutorials, talks, and updates on the TensorFlow framework.
TensorFlow
PyTorch (channel)
Official channel with tutorials, conference talks, and updates on the PyTorch framework.
PyTorch
Kaggle (channel)
Official Kaggle channel with data science competition walkthroughs and machine learning talks.
Kaggle
AI Explained (channel)
Analysis of frontier AI model releases, benchmarks, and their broader implications.
AI Explained
CS188: Introduction to Artificial Intelligence
UC Berkeley's foundational AI course covering search, planning, and machine learning.
UC Berkeley
6.034 Artificial Intelligence, Fall 2010
Classic MIT AI course covering search, reasoning, learning, and neural networks.
MIT OpenCourseWare (Patrick Winston)
11-785 Introduction to Deep Learning (Spring 2020)
CMU's graduate deep learning course covering architectures, optimization, and applications.
Carnegie Mellon University
Abhishek Thakur (channel)
Kaggle Grandmaster's channel on applied machine learning, NLP, and competitive data science.
Abhishek Thakur
Full Stack Deep Learning – 2022
Course on taking deep learning models from prototype to production-grade systems.
Full Stack Deep Learning
Serrano.Academy (channel)
Illustration-driven explanations of machine learning and mathematics concepts by Luis Serrano.
Luis Serrano
Supervised Machine Learning: Regression and Classification
Free-to-audit video lectures updating Andrew Ng's classic machine learning course.
DeepLearning.AI & Stanford Online (Coursera)
Deep Learning Specialization
Free-to-audit video lecture specialization covering neural networks, CNNs, RNNs, and more.
DeepLearning.AI (Coursera)
Natural Language Processing Specialization
Free-to-audit video lectures on NLP techniques from classical methods to transformers.
DeepLearning.AI (Coursera)
Machine Learning Engineering for Production (MLOps) Specialization
Free-to-audit video lectures on deploying and maintaining machine learning systems in production.
DeepLearning.AI (Coursera)
AI For Everyone
Free-to-audit non-technical video course explaining what AI can and cannot do for organizations.
DeepLearning.AI (Coursera)
Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning
Free-to-audit video course teaching TensorFlow best practices for building neural networks.
DeepLearning.AI (Coursera)
CS50's Introduction to Artificial Intelligence with Python
Free-to-audit Harvard video course covering AI search, knowledge, learning, and neural networks.
HarvardX (edX)
Statistics Fundamentals
Playlist explaining core statistics concepts clearly with simple visual examples.
StatQuest with Josh Starmer
Essence of Linear Algebra
Visual, intuition-first playlist covering vectors, matrices, and linear transformations.
3Blue1Brown
Essence of Calculus
Visual playlist building geometric intuition for derivatives, integrals, and limits.
3Blue1Brown
MIT 18.06 Linear Algebra, Spring 2005 Lectures
Gilbert Strang's full recorded lecture series for MIT's linear algebra course.
MIT OpenCourseWare (Gilbert Strang)
CS231n Spring 2017 Lectures
Full recorded Stanford lecture series on convolutional neural networks and vision.
Stanford University
MIT OpenCourseWare YouTube Channel
Channel hosting full free video lecture series across MIT's math and CS courses.
MIT OpenCourseWare
StatQuest Machine Learning Basics with StatQuest
Main channel for StatQuest's free video lessons on statistics and machine learning.
StatQuest with Josh Starmer