70015 Mathematics for Machine Learning
Imperial College London
1. Multivariate Calculus (einstein notation, differentiation and integration);
2. Multivariate probability (joint pmfs, joint pdfs, means, covariance matrices);
3. Conditional probability and Bayes's rule;
4. Maximum Likelihood estimation;
5. Monte Carlo Estimation;
6. Validation and test error estimation, and cross - validation;
7. Concentration inequalities;
8. Gradient descent and its convergence;
9. PCA, eigendecomposition, SVD;
10. Bayesian inference;
11. MAP inference;
12. Multivariate Gaussians;
13. Bayesian Linear Regression
CS234 Reinforcement Learning
Stanford University
1. Introduction to Reinforcement Learning;
2. Making Sequences of Good Decisions Given a Model of the World;
3. Model - Free Policy Evaluation Policy Evaluation Without Knowing How the World Works;
4. Model Free Control and Function Approximation;
5. Policy Gradient I;
6. Policy Gradient II. Advanced policy gradient s...des from Joshua Achiam’s slides, with minor modifications;
7. Policy Gradients and Imitation Learning;
8. Imitation Learning and RLHF;
9. RLHF and Guest Lecture on Values and Alignment;
10. Batch / Offline RL Policy Evaluation & Optimization;
11. Data Efficient Reinforcement Learning;
12. Fast Reinforcement Learning;
13. Fast Reinforcement Learning;
14. Fast RL Continued
EE6222 Machine Vision
Nanyang Technological University
1. Image Fundamentals and Human Perception;
2. LSI Systems and Transforms;
3. Image Denoising and Enhancement;
4. Morphological Image Processing;
5. Intuitive Understanding of Object Recognition;
6. MAP Decision and Classifiers;
7. Statistical Estimation and Machine Learning;
8. Handcrafted Feature Generation and Feature Selection;
9. Visual Data Dimensionality Reduction as Feature Extraction;
10. Neural Networks and Deep Machine Learning;
11. Deep Learning from CNN to Transformer;
12. Video Analysis;
13. Video Recognition;
14. 3D Machine Perception;
15. 3D Machine Vision
EE6405 Natural Language Processing
Nanyang Technological University
1. Introduction to NLP;
2. Linguistic Analysis and Information Extraction;
3. Term Weighting Scheme_For Students_final version;
4. Traditional ML and NLP Applications;
5. Evaluation Metrics Word Embeddings;
6. Neural Language Models;
7. Transformers;
8. Hyper Parameter Tuning;
9. Transformer Based Large Language Models;
10. A Survey of NLP Applications Across Diverse Industries;
11. Deep-dive into NLP Applications
EE6407 Genetic Algorithms & Machine Learning
Nanyang Technological University
1. Introduction to Machine Learning;
2. Data Preparation for Machine Learning;
3. Bayesian Decision Theory;
4. Linear Discriminant Analysis;
5. Support Vector Machines;
6. Classification Trees;
7. Performance Evaluation for Classifiers;
8. Regression;
9. Feature Selection for Dimensionality Reduction and Classification;
10. Clustering Analysis;
11. Clustering Evaluation
EE6483 Artificial Intelligence & Data Mining
Nanyang Technological University
1. AI Introduction and Brief History;
2. Structures and Strategies for State Space Search;
3. Heuristic Search and Gaming;
4. Introduction to Data Mining and Association Analysis;
5. Introduction to Machine Learning;
6. Classification and Decision Trees;
7. Nearest Neighbor Classifiers;
8. Support Vector Machines;
9. Neural Networks;
10. Clustering and Regression;
11. Regularization and Optimization;
12. PCA and Bayesian Inference;
13. Summary and More Examples
EE6497 Pattern Recognition & Deep Learning
Nanyang Technological University
1. Introduction, Probability Review;
2. Bayesian Inference;
3. Mixture Models and the EM Algorithm;
4. Markov Models and HMM;
5. Sampling;
6. Markov Chain Monte Carlo (MCMC);
7. Introduction to Neural Networks and Deep Learning;
8. Training Deep Networks;
9. Convolutional Neural Networks (CNNs);
10. Recurrent Neural Networks (RNNs);
11. Generative Models;
12. Self-Supervised Learning