-
Supervised learning (Chapter 2)
-
Multivariate method (Chapter 5)
-
Linear discrimination (Chapter 10)
-
Mutilayer perceptron (Chapter 11)
-
Feasibility of learning, VC dimension
-
Overfitting and regularization
-
DNN (Chapter 12)
-
Support vector machine(SVM) and Kernel method (Chapter 14)
-
Reinforcement learning (Chapter 19)
The machine learning course(EE 370000) is taught by Prof. Ya-Tang Yang based the classic textbook by Ethem Alpaydin. The fundamental concepts and techniques are explained in detail. The focus of the lectures is real understanding, not just "knowing.
Textbook:
Ethem Alpaydin, “introduction to machine learnig”, 4th edition, MIT Press.
This course aims to give students an overview of the theoretical foundations and applications of artificial neural networks that have been implemented in software and hardware. It will discuss typical topics, including from the perspective of statistical learning theory, rigorous A discussion of the statistical basis of learning, such as training and testing of neural networks, VC dimension and model complexity, regularization as a remedy for overfitting measure.
Additionally, we would like to introduce a number of specific neural network models, some rooted in statistical physics and some in biology. For example, Hopfield model, Boltzmann machine, spiking neural network and self-organization mapping. These are relatively special topics in machine learning or artificial intelligence courses, so they are usually not covered. will involve. The course will also require students to do coding.
Textbook:
Aurelien Geron, Hands on machine learning with Scikit-Learn,
Keras & TensorFlow, 2nd edition, O’Reilly. (Chinese version available)
Special topics in artificial neural network
(offered in Autumn in 2023)