Machine Learning – Fall 2006

ICS: 273A
Instructor: Max Welling
 


Prerequisites

ICS 270A Intro AI, or with consent of instructor.


Goals:

The goal of this class is to familiarize you with various stat-of-the-art machine learning techniques for
classification, regression, clustering and dimensionality reduction. Besides this, an important aspect
this class is to provide a modern statistical view of machine learning.

Through projects you will learn to do independent research on some real world datasets.


Homework : Please see green boxes on the slides.

Projects: Submit a one page description with detailed info about what you like to do,
or default to
one of these.

CRAWDAD data

Netflix site


Syllabus:

1: introduction: overview, examples, goals, algorithm evaluation, statistics, kNN, logistic regression. [ slides lec1] [slides lec2]

2: classification I: decision trees, random forests, bagging, boosting,. [slides lec3,4]

3: clustering & dimensionality reduction: k-means, expectation-maximization, PCA. [slides lec5,6]

4: neural networks: perceptron, multi-layer networks, back-propagation. [slides lec7,8]

5: reinforcement learning: MDPs, TD- and Q-learning, value iteration. [slides lec9,10]

6: Bayesian methods: conditional independence, generative models, naive Bayes classifier. [slides lec11,12 ]

7: classification II: kernel methods & support vector machines. [slides lec13,14]
required reading on SVM [classnotes SVM].
Additional background reading [classnotes convex optimization]

In the last week we will do do class presentations of your projects. Please prepare 10 mins talks

Final + ansers


Syllabus:

The course will primarily be lecture-based with homework and
exams. Most homework will revolve around the implementation of various
classification algorithms on the SciTech dataset provided above.
It is required that you use MATLAB for this coding work.


Grading Criteria


Grading will be based on a combination of weekly homework (10%) ,  projects  (35%), some midterm (20% ) and a final exam (35%) .


Textbook


The textbook that will be used for this course is:

1. Tom Mitchell: Machine Learning. (http://www.cs.cmu.edu/~tom/mlbook.html)


Optional side readings are:

2. D. MacKay: Information Theory, Inference and Learning Algorithms
3. R.O. Duda, P.E. Hart, D. Stork: Pattern Classification
4. C.M. Bishop: Neural Networks for Pattern Recognition
5. T. Hastie, R. Tibshirani, J.H, Friedman: The Elements of Statistical Learning
6. B.D. Ripley: Pattern Recognition and Neural Networks