SYLLABUS
Contact Information:

Time	MWF: 8 - 9 AM
Place	330 Simrall
Instructor	Joseph Picone, Professor
Office	413 Simrall
Office Hours	9-10 MWF (others by appt.)
Email	picone@cavs.msstate.edu
Class Alias	ece_8990_pr@cavs.msstate.edu
URL	http://www.cavs.msstate.edu/research/isip/publications/courses/ece_8990_pr
Textbook	R.O. Duda, P.E. Hart, and D.G. Stork, Pattern Classification, Second Edition, Wiley Interscience, ISBN: 0-471-05669-3, 2000
Suggested Reference	R. Schalkoff, Pattern Recognition: Statistical, Structural, and Neural Approaches, Wiley Interscience, ISBN: 0-471-52974-5, 1992
Prerequisite	Statistics, Signal Processing, many years of research, and attendance at a lecture where the speaker proudly exclaimed "PCA Fails!"
Other Reference Materials	Pattern Recognition Applet Statistical Signal Processing Publications Statistical Signal Processing Software Internet Links

Grading Policies:

Item:	Due Date:	Weight:
Critical Review No. 1	02/06	33%
Critical Review No. 2	03/20	33%
Final Exam	05/09	34%

Critical Reviews:

For each critical review, you will select a contemporary paper, published within the last two years, and provide a crtique of the algorithm. These papers will be exactly four pages in length and follow an IEEE conference style format. See examples for examples of this conference format. Students must provide the source document (Frame, MS Word, etc.) and a pdf file. Papers will be submitted electronically by providing the instructor with a URL from which the paper can be retrieved.

Final Exam:

For the final exam, you will select an algorithm, perform a blind evaluation of the algorithm using the data provided by the instructor, and write a four-page paper analyzing the results. Grades will be assigned based on how well you do relative to published performance and your peers, as well as the quality of your analysis.

Attendance / Survival:

Attendance does not figure directly into your grade. However, historically students who do not attend class regularly do not do well in this class. Further, most students end up with a grade on a borderline at the end of the semester. In this case, I use attendance and classroom participation to determine the final grade.

Schedule:

Class	Date	Sections	Topic
1	01/08	1.1	Introductions
2	01/10	1.2, 1.3	Overview: Pattern Recognition in Action
3	01/12	2.1, 2.2	Bayes' Decision Theory
4	01/17	2.3 - 2.5	Classifiers and Discriminant Functions
5	01/19	2.6, 2.7	Gaussian Densities
6	01/22	2.8, 2.9	Error Bounds, Discrete Features
7	01/24	2.10, 2.12	Missing Features, Context
8	01/26	2.10	Bayesian Belief Networks
9	01/29	3.1-3.3	Maximum Likelihood Parameter Estimation
10	01/31	3.5	Bayesian Parameter Estimation
11	02/02	3.6, 3.7	Sufficient Statistics
12	02/05	3.8	Component Analysis
13	02/07	3.8	Discriminant Analaysis
14	02/09	3.9	Expectation-Maximization
15	02/12	3.10	Hidden Markov Models - Overview
16	02/14	3.10	Definitions and Basic Calculations
17	02/16	3.10	Training and Learning
18	02/19	3.10	Continuous Distributions and Mixtures
19	02/21	4.1 - 4.3	Parzen Window
20	02/23	4.5 - 4.9	Nearest Neighbor
21	02/26	5.1 - 5.3	Linear Discriminant Functions
22	02/28	5.4 - 5.6	Two-Class Linearly Separable Data
23	03/02	5.7 - 5.12	Support Vector Machines
24	03/05	6.1 - 6.3	Multilayer Networks, Backpropagation
25	03/07	6.4 - 6.9	Bayes Theory, Practical Issues
26	03/09	6.10, 6.11	Additional Networks, Regularization
27	03/19	7.1 - 7.2	Simulated Annealing
28	03/21	7.3 - 7.4	Boltzmann Machines
29	03/23	7.5 - 7.6	Evolutionary Methods
30	03/26	8.1 - 8.2	Decision Trees
31	03/28	8.3 - 8.4	CART
32	03/30	8.5	String Matching
33	04/02	8.6	Grammatical Methods
34	04/04	8.7	Rule Based Systems
35	04/06	9.1	Occam's Razor
36	04/09	9.2	No Free Lunch Theorem
37	04/11	9.3	Minimum Description Length
38	04/16	9.4 - 9.5	Resampling Techniques
39	04/18	9.6 - 9.7	Comparing and Combining Classifiers
40	04/20	10.1 - 10.3	Unsupervised Learning
41	04/23	10.4 - 10.7	Clustering
42	04/25	10.8 - 10.14	Advanced Clustering Techniques
43	04/27	Review	Parameter Estimation
44	04/30	Review	Classification Based on Noisy Parameters
45	05/02	Review	Speech Recognition Applications
46	05/05	Final Exam	Evaluation Deadline