Advanced Machine Learning

Introduction
This course systematically introduces the fundamental algorithms and theories of machine learning, with an emphasis on the mathematical principles, model derivation, and practical applications of machine learning methods. The course covers regression, classification, support vector machines, neural networks, generative models, and clustering.

Instructor: Qing-Yuan Jiang (jiangqy@njust.edu.cn)
TA: Peng Cheng.
Location: Room III-514.
Note: Please send your PPT file to the teaching assistant one day in advance.

Course Agenda:

Date	Lectures	Topic	Handouts
Part I: Foundations of Machine Learning
Thu. Sept. 17	Course Overview	Course Information Course Assessment	[Slide]
Thu. Sept. 17	Introduction to ML	Background, Definition Applications	[Slide]
Fri. Sept. 18	Optimization for Machine Learning	Convex Optimization Stochastic Gradient Descent	[Slide]
Fri. Sept. 24	Model Selection and Evaluation	Model Selection and Evaluation	[Slide]
Part II: Machine Learning Models
Thu. Oct. 8	Linear Models & Logistic Regression	Linear Model Logistic Regression	[Slide]
Thu. Oct. 8	Tree-Based Models & Ensemble Models	Decision Tree Forest Ensemble Learning Boosting	[Slide]
Thu. Oct. 15	Margin-Based Models	Support Vector Machine Kernel Method	[Slide]
Part III: Deep Learning
TBD	Neural Network Fundamentals	TBD TBD	[Slide]
TBD	Neural Network Architectures	TBD TBD	[Slide]
Part IV: Foundation Models
TBD	Representation Learning	TBD TBD	[Slide]
TBD	Vision-Language Models	TBD TBD	[Slide]
TBD	Large Language Models	TBD TBD	[Slide]