Course Desc<x>ription:
<br>Machine learning is programming computers to optimize a performance criterion using example data or past 
<br>experience. We need learning in cases where we cannot directly write a computer program to solve a given 
<br>problem. This course discusses may methods that have their ba<x>ses in different fields: statistics, pattern 
<br>recognition, neural network, artificial intelligence, signal processing, control, and data mining. Examples from 
<br>wide variety of subject such as biology, control, statistical mechanics and robotics will be given as proper 
<br>context for machine learning. Programming codes as embodiment of the algorithm in machine learning will be 
<br>analyzed in details. 
<br>
<br>Syllabus
<br>1. Introduction; probability theory and statistics; things you need for computational thinking; random number 
<br>generator and Monte Carlo method  
<br>2. Supervised learning
<br>3. Baysian decision theory
<br>4. Parametric method
<br>5. Multivariate method
<br>6. Clustering
<br>7. non-parametric method
<br>8. linear discriminant
<br>9. multi-la<x>yer perceptron; neural network
<br>10. Deep learning
<br>11. Reinforcement learning 
<br>12. Special topics on current research frontier (spiking neuron network)
<br>
<br>
<br>Textbook
<br>1. Ethem Alpaydin, Introduction to machine learning, 4th edition, MIT Press.
<br>
<br>References:
<br>1. Artificial Intelligence, Stuart Russel and Peter Norvig, Prentice Hall.1995
<br>2. Masashi Sugiyama, Statistical Reinforcement Learning CRC
<br>3. Duda, R.O. P. E. Hart, and D. G. Stork 2001 Pattern Classification, 2nd ed. New York: Wiley. (Excellent book 
<br>on neural network. Plenty of good figures to study.)
<br>
<br>Method:
<br>Powerpoint sides will be used for teaching. 
<br>
<br>Grading& Evaluation
<br>Homework (40%) and Midterm and final exam (60%)
<br>