Created:
Tue 04 Sep 2012
Last modified:
Note: This is an approximate syllabus; it may change at any time.
- Lecture 01, Wed, Sep 05 2012
- Admistrivia
- Introduction to Machine Learning
- Reading: DHS Chap. 1, A.4
- Lecture 02, Wed, Sep 12 2012
- Probability primer
- Homework 01 assigned
- Reading: DHS Chap. A.4
- Lecture 03, Wed, Sep 19 2012
- Finish probability primer
- Bayesian methods
- Parameter estimation
- Homework 01 due
- Homework 02 assigned
- Reading: DHS Chap. 2
- Lecture 04, Wed, Sep 26 2012
- Finish Bayesian methods
- Finish parameter estimation
- Start regression and logistic regression
- Reading: DHS Chap. 2, 3, 5
- Lecture 05, Wed, Oct 03 2012
- Performance analysis
- Training regression and logistic regression
- Homework 02 due
- Homework 03 assigned
- Reading: DHS Chap. 9.6, 5, 6
- Lecture 06, Wed, Oct 10 2012
- Finish regression, logistic regression, gradient descent
- Perceptrons and neural networks
- Reading: DHS Chap. 5, 6
- Lecture 07, Wed, Oct 17 2012
- Information Theory primer
- Decision trees
- Homework 03 due
- Reading: DHS Chap. A.7, 8
- Lecture 08, Wed, Oct 24 2012
- Finish decision trees
- Start ensemble methods: boosting, bagging
- Reading: DHS Chap. 8, 9.5
- Lecture 09, Wed, Oct 31 2012
- Finish boosting
- On-line learning:
- halving algorithm
- randomized halving algorithm
- weighted majority algorithm
- Lecture 10, Wed, Nov 07 2012
- Finish on-line learning:
- Multiclass prediction: ECOC
- Lecture 11, Wed, Nov 14 2012
- Machine learning theory: PAC learning
- Lecture 12, Wed, Nov 28 2012
- Finish machine learning theory: PAC learning
- Nearest neighbor techniques
- k-NN
- collaborative filtering
- MDL: the minimum description length principle
- Reading: DHS Chap. 4.4-6, 9.2.3-4
- Lecture 13, Wed, Dec 05 2012
- Final Project
- Due date: Tue, Dec 11 2012
Switch to:
jaa@ccs.neu.edu