CS 115: Neural Networks.

Instructor           Jaime Davila
Office              : ASH 204
Office Hrs       : Tuesdays and Thursdays, 9:30-10:30
                              Monday and Wednesdays, 1-2:30,
                              or by appointment.
Phone Number : 413-559-5687
email               : jdavila at hampshire dot edu (by far the best way to reach me)

This course is designed to give you an introduction to the field of artificial neural networks (ANN). Emphasis will be placed on hands-on experience via online investigation of active research in the field, as well as the design and implementation of our own projects.

Students are expected to actively contribute to the course. There will be weekly homeworks having to do with investigating how others have dealt in practice with the theory we see in class, as well as the design of our own projects. We will be implementing our own projects with a neural network simulator called SNNS (Stuttgard Neural Network Simulator). Accounts will be created so that students can gain access to this software locally at Hampshire College.

Your evaluation for this course will be based on 1) class participation, 2) short papers (1-2 pages) reporting how other scientists are using NN in their research, 3) the design and possibly the implementation of a research project having to do with NN.

Some online resources.

1) NN Frequently asked questions (FAQ)

2) The SNNS website

3) Our class mailing list.

4) My own personal webpage related to NN, and some of my published articles.

5) A sample NN file for SNNS.

6) A sample pattern file for SNNS.

7) A sample batchman file for SNNS (call it with the command 'batchman - f name_of_batch_file -l name_of_log_file)..

8) A A sample NN paper. It is still being written, so you can quickly see the outline it follows. The sections that HAVE been written already are the minimum you must write in order to recieve 1/2 of a two course option for a div I. For a project based division I you must write the complete paper. The file is in PDF (Adobe acrobat) format.

Below is an outline of the topics we will discuss this semester. All of the basic material will be presented in class, but no textbook will be assigned. For this reason, attendance to all classes is HIGHLY recommended. Students are also encouraged to research online on the topics we will be seeing in class.

Bear in my, also, that some topics will be introduced as needed based on the conversations we will be having in class. Whenever we do, I will update this syllabus to reflect the topics covered.

Week	Dates	Topics
1	Jan. 29	Course outline. What you should expect of the course. Office hours, etc. Introduction to the course. What can NN do, what they are typically used for. Definition of an artificial neuron. First look at a neural network.
2	Feb. 3, 5	Reading papers about NN. Finding papers about NN.
3	Feb. 10, 12	Reading papers about NN. Selection of semester-long projects.
4	Feb. 17, 19	Writing a 'statement of purpose' for a NN experiment. (Writing an abstract)
5	Feb. 24, 26	Finding background information. (creating a bibliography)
6	Mar. 3, 5	Describing your project.
7	Mar. 10, 12	Running experiments. (SNNS)
8	Mar. 17, 19	Spring break.
9	Mar. 24, 26	Running experiments. (SNNS)
10	Mar. 31, Apr. 2	Results analysis.
11	Apr. 7	Playing devil's advocate.
12	Apr. 14, 16	Result validation.
13	Apr. 21, 23	Documenting results. Establishing future research opportunities.
14	Apr. 28, 30	Class presentations.