CS420 Machine Learning 2019 

Weinan Zhang, Assistant Professor

Zhiyuan College
Shanghai Jiao Tong University

Email: wnzhang [AT] sjtu.edu.cn

Machine learning is the science of training machines with non-explicit programming based on a dataset to get them work on intelligent tasks. Machine learning has obtained fast development during the last two decades and now plays an important role in various aspects of our daily life, such as weather forecasting, e-commerce personalized recommendation, news categorization, face recognition, speech QA, self-driving, home robots, and medical expert system etc. Particularly, in March 2016, Google's AlphaGo beat Lee Se-dol on Game of Go with the score 4-1, which indicates the arrival of the new artificial (general) intelligence era with machine learning based on big data.

This course provides a comprehensive introduction of the fundamental problems and methodologies of machine learning, including supervised/unsupervised learning (covering most prediction applications, e.g., recommender systems, image recognition and webpage ranking etc.) and reinforcement learning (covering all decision-making applications, e.g., playing Go, self-driving, ad bidding and smart stock picking etc.). Additionally, the coursework includes hands-on tasks, in which the students are required to design machine learning programs to accomplish several intelligence tasks, and are highly encouraged to further improve the machine performance via trying different models and refining the code implementation.

Notice

Two course works have been released!

Course Works


link
Course work 1: Text Classification for Sentiment Analysis
To create a classification model sentiment analysis of review comments.
Mar. 11 - Apr. 22, 2019.

link
Course work 2: Click Prediction of Recommender Systems
To create a user click-through rate prediction model for recommender system.
Mar. 11 - Apr. 22, 2019.

Slides


pdf
Lecture 1: Introduction to Machine Learning
Introduction about AI, machine learning, data science and various ML applications
Feb. 25, 2019

pdf
Home Reading 1A: Mathematics for Machine Learning
Mathematic fundamentals for machine learning, including Algebra, Probabilistic, Statistics and Optimization etc.
Feb. 25, 2019

pdf
Lecture 2: Linear Models for Supervised Learning
Discriminative/generative models, linear regression, logistic regression
Mar. 4, 2019

pdf
Lecture 3: Support Vector Machine and Kernel Methods
Maximizing Margin Classification, SVMs, Convex Optimization, Kernel Tricks
Mar. 11, 2019

pdf
Lecture 4: Neural Networks
Perceptron, Multilayer Perceptron, Backprop, Deep Learning
Mar. 18, 2019

pdf
Lecture 5: Tree Models
Decision Trees, ID3, CART
Mar. 25, 2019

pdf
Lecture 6: Ensemble and Boosting Algorithms
Ensemble methods, Bagging, Boosting
Apr. 1, 2019

pdf
Lecture 7: Ranking and Filtering
Learning to rank, collaborative filtering, matrix factorization
Apr. 8, 2019

pdf
Lecture 8: Probabilistic Graphical Models
Bayes Network, Markov Network, Conditional Independence, Message Passing
Apr. 15-22, 2019

pdf
Lecture 9: Unsupervised Learning
PCA, Mixture Gaussians, EM Methods, Auto-encoders, GANs
Apr. 29, 2019

pdf
Lecture 10: Learning Theory and Model Selection
PAC Learning Theory, VC Demension, Bias Variance Decomposition, Feature Selection
May 6, 2019

pdf
Lecture 11: Introduction to Reinforcement Learning
Reinforcement Learning, Markov Decision Process, Dynamic Programming, Model-free RL
May. 13, 2019

pdf
Lecture 12: Approximation Methods in RL
Value Approximation Methods, Policy Gradients, Actor Critic
May. 20, 2019

pdf
Lecture 13: Deep Reinforcement Learning
Deep Q-Networks, Trust Region Policy Gradient, Deep Deterministic PG
May. 27, 2019

pdf
Lecture 14: Multi-Agent Reinforcement Learning
Stochastic Games, Nash Q-Learning, Mean-Field Q-Learning
May. 27, 2019

pdf
Lecture 15: Transfer Learning
Transfer Learning, Domain Adaptation, Importance Sampling, Parameter Sharing
Jun. 3, 2019

pdf
Lecture 16: Meta Learning
Meta Learning, Learning to Learning, MAML, RNN4SGD, RL4SGD
Jun. 3, 2019

Related Readings

Teaching Assistants


link
Zhou Fan, ACM16 student, research intern in ApexLab
Research on reinforcement learning and mechanism design.
Email: zhou.fan [AT] sjtu.edu.cn

link
Siyuan Feng, ACM16 student, research intern in ApexLab
Research on urban data computing, machine learning system and reinforcement learning.
Email: hzfengsy [AT] sjtu.edu.cn

link
Yutong Xie, ACM16 student, research intern in ApexLab
Research on natural language processing and multi-task learning.
Email: xxxxxyt [AT] sjtu.edu.cn

Past Courses


link
CS420 Machine Learning 2018
Compared to CS420 2018, CS420 2019 will be more comprehensive on multi-agent reinforcement learning and meta-learning. The course works will be more practical and close to industry.

link
CS420 Machine Learning 2017
Compared to CS420 2017, CS420 2018 adds more materials on (multi-agent) reinforcement learning.

News


Mar. 11, 2019
First two course works are published.

Feb. 27, 2019
Zhou Fan, Siyuan Feng and Yutong Xie appointed as the teaching assitants of CS420 2019.

Feb. 25, 2019
Course started!