Course Description:
Machine learning is programming computers to optimize a performance criterion using example data or past
experience. We need learning in cases where we cannot directly write a computer program to solve a given
problem. This course discusses may methods that have their bases in different fields: statistics, pattern
recognition, neural network, artificial intelligence, signal processing, control, and data mining. Examples from
wide variety of subject such as biology, control, statistical mechanics and robotics will be given as proper
context for machine learning. Programming codes as embodiment of the algorithm in machine learning will be
analyzed in details.

Syllabus
1. Introduction; probability theory and statistics; things you need for computational thinking; random number
generator and Monte Carlo method
2. Supervised learning
3. Baysian decision theory
4. Parametric method
5. Multivariate method
6. Clustering
7. non-parametric method
8. linear discriminant
9. multi-layer perceptron; neural network
10. Deep learning
11. Reinforcement learning
12. Special topics on current research frontier (neuronal dynamics, spiking neuron network and Hopfield
model)


Textbook
1. Ethem Alpaydin, Introduction to machine learning, 4th edition, MIT Press.

References:
1. Artificial Intelligence, Stuart Russel and Peter Norvig, Prentice Hall.1995
2. Duda, R.O. P. E. Hart, and D. G. Stork 2001 Pattern Classification, 2nd ed. New York: Wiley. (Excellent book
on neural network. Plenty of good figures to study.)

Method:
Powerpoint sides will be used for teaching.

Grading& Evaluation
Homework (20%) and Midterm and final exam (80%)


採用下列何項 AI 使用規則 (Indicate which of the following options you use to manage student use of the AI)

禁止使用,請註明相關的監管機制 Prohibited use; please specify relevant oversight

there will be some random checking of usage of AI tool such as ChapGPT.
Our course is the core of AI course so basically, all the homework design will be aimed to to outsmart the
commercial AI tool.