At dair.ai we β€οΈ open education. We are excited to share some of the best and most recent machine learning courses available on YouTube.
Course List:
- Stanford CS229: Machine Learning
- Applied Machine Learning
- Machine Learning with Graphs (Stanford)
- Probabilistic Machine Learning
- Introduction to Deep Learning (MIT)
- Deep Learning: CS 182
- Deep Unsupervised Learning
- NYU Deep Learning SP21
- CMU Neural Networks for NLP
- Multilingual NLP
- Advanced NLP
- Deep Learning for Computer Vision
- Deep Reinforcement Learning
- Full Stack Deep Learning
- AMMI Geometric Deep Learning Course (2021)
To learn some of the basics of ML:
β’ Linear Regression and Gradient Descent β’ Logistic Regression β’ Naive Bayes β’ SVMs β’ Kernels β’ Decision Trees β’ Introduction to Neural Networks β’ Debugging ML Models ...
π Link to Course
To learn some of the most widely used techniques in ML:
β’ Optimization and Calculus β’ Overfitting and Underfitting β’ Regularization β’ Monte Carlo Estimation β’ Maximum Likelihood Learning β’ Nearest Neighbours ...
π Link to Course
To learn some of the latest graph techniques in machine learning:
β’ PageRank β’ Matrix Factorizing β’ Node Embeddings β’ Graph Neural Networks β’ Knowledge Graphs β’ Deep Generative Models for Graphs ...
π Link to Course
To learn the probabilistic paradigm of ML:
β’ Reasoning about uncertainty β’ Continuous Variables β’ Sampling β’ Markov Chain Monte Carlo β’ Gaussian Distributions β’ Graphical Models β’ Tuning Inference Algorithms ...
π Link to Course
To learn some of the fundamentals of deep learning:
β’ Introduction to Deep Learning
π Link to Course
To learn some of the widely used techniques in deep learning:
β’ Machine Learning Basics β’ Error Analysis β’ Optimization β’ Backpropagation β’ Initialization β’ Batch Normalization β’ Style transfer β’ Imitation Learning ...
π Link to Course
To learn the latest and most widely used techniques in deep unsupervised learning:
β’ Autoregressive Models β’ Flow Models β’ Latent Variable Models β’ Self-supervised learning β’ Implicit Models β’ Compression ...
π Link to Course
To learn some of the advanced techniques in deep learning:
β’ Neural Nets: rotation and squashing β’ Latent Variable Energy Based Models β’ Unsupervised Learning β’ Generative Adversarial Networks β’ Autoencoders ...
π Link to Course
To learn the latest neural network based techniques for NLP: β’ Language Modeling β’ Efficiency tricks β’ Conditioned Generation β’ Structured Prediction β’ Model Interpretation β’ Advanced Search Algorithms ...
π Link to Course
To learn the latest concepts for doing multilingual NLP:
β’ Typology β’ Words, Part of Speech, and Morphology β’ Advanced Text Classification β’ Machine Translation β’ Data Augmentation for MT β’ Low Resource ASR β’ Active Learning ...
π Link to Course
To learn advanced concepts in NLP:
β’ Attention Mechanisms β’ Transformers β’ BERT β’ Question Answering β’ Model Distillation β’ Vision + Language β’ Ethics in NLP β’ Commonsense Reasoning ...
π Link to Course
To learn some of the fundamental concepts in CV:
β’ Introduction to deep learning for CV β’ Image Classification β’ Convolutional Networks β’ Attention Networks β’ Detection and Segmentation β’ Generative Models ...
π Link to Course
To learn about concepts in geometric deep learning:
β’ Learning in High Dimensions β’ Geometric Priors β’ Grids β’ Manifolds and Meshes β’ Sequences and Time Warping ...
π Link to Course
To learn the latest concepts in deep RL:
β’ Intro to RL β’ RL algorithms β’ Real-world sequential decision making β’ Supervised learning of behaviors β’ Deep imitation learning β’ Cost functions and reward functions ...
π Link to Course
To learn full-stack production deep learning:
β’ ML Projects β’ Infrastructure and Tooling β’ Experiment Managing β’ Troubleshooting DNNs β’ Data Management β’ Data Labeling β’ Monitoring ML Models β’ Web deployment ...
π Link to Course
There are many plans to keep improving this collection. For instance, I will be sharing notes and better organizing individual lectures in a way that provides a bit of guidance for those that are getting started with machine learning.
If you are interested to contribute, feel free to open a PR with links to all individual lectures for each course. It will take a bit of time, but I have plans to do many things with these individual lectures. We can summarize the lectures, include notes, provide additional reading material, include difficulty of content, etc.