CS110 Course Handout (Fall 1998)

Bryn Mawr College
CS 380: Recent Advances in Computer Science
Evolutionary Robotics
Spring 1999
Course Materials

Information
Texts Important Dates Assignments Lectures Grading Links

General Information

Instructor: Deepak Kumar, 248 Park Hall, 526-7485
E-Mail: dkumar@brynmawr.edu
WWW: http://mainline.brynmawr.edu/~dkumar

Lecture Hours: Tuesdays & Thursdays, 10:00 a.m. to 11:00 a.m.
Room: Park 338

Description: This course will cover computer-based representational formalisms and algorithms that facilitate learning behaviors and that are inspired by biological models. We will focus on connectionist models that are based on neural network abstractions. We will also cover evolution-based approaches such as genetic algorithms, genetic programming, and evolutionary programming, discussing the kinds of learning behaviors facilitated by them.

Texts & Software

Understanding Neural Networks, Volume 1: Basic Networks, by Caudill & Butler, MIT Press, 1992.
Rethinking Innateness: A Connectionist Perspective on Development, by Elman, Bates, Johnson, Karmiloff-Smith, Parisi, and Plunkett, MIT Press, 1996.
Exercises in Rethinking Innateness: A Handbook for Connectionist Simulation, by Plunkett & Elman, MIT Press.

Important Dates

January 19 : First class meeting
April 29: Last class meeting

Assignments

Lab#1: The Kohonen Network Simulator: Do all the exercises from Chapter 6 (Caudill & Butler).

Lectures

Week 1 (January 19, 21)
January 19: First Class Meeting. Administrative/logistics.
January 21: Introduction to Neural Networks: Perceptron
Read: Chapter 1, 2, 3 from Caudill & Butler. Try all exercises from Chapter 3.
Week 2 (January 26, 28)
January 26: Review of Perceptron, Minimum Error Learning: Adaline. Unsupervised Learning: The Kohonen Network.
Read: Chapter 4 & 6 from Caudill & Butler. Try all exercises from Chapter 4.
January 28: Lab: The Kohonen Network Simulator: Do all the exercises from Chapter 6.
Week 3 (February 2, 4)
February 2:
February 4:
Week 4 (February 9, 11)
February 9:
February 11:
Week 5 (February 16, 18)
February 16: Backprop.
February 18: Backprop.
Week 6 (February 23, 25):
February 23: Rethinking Innateness (Chapter 1 & 2).
February 25: Exercises in Rethinking Innateness (Chapters 1, 2 & 3).
Week 7 (March 2, 4)
March 2: Finish the exercises from Chapter 3: Exercises in Rethinking Innateness.
March 4: Finish the exercises from Chapter 4: Exercises in Rethinking Innateness.
Week 8 (March 9, 11): Spring Break: No classes this week.
Week 9 (March 16, 18)
March 16: Finish exercises from Chapter 5: Exercises in Rethinking Innateness.
March 18: Discussion: Neural Network Applications & individual projects.
Week 10 (March 23, 25)
March 23: Cluster Analysis. Finish exercises from Chapter 6: Exercises in Rethinking Innateness.
Read:
Rule Inference for Financial Prediction using Recurrent Neural Networks, by Giles, Lawrence, Tsoi, IEEE CIFE, 1997.
Revealing the Structure of NETtalk's Internal Representations, by Charles Rosenberg, COGSCI-87.
March 25: No meeting today, I am out of town attending ACM SIGCSE-1999.
Week 11 (March 30, April 1)
March 30: Discussion on readings.
April 1:
Week 12 (April 6, 8)
April 6:
April 8:
Week 13 (April 13, 15)
April 13:
April 15:
Week 14 (April 20, 22)
April 20:
April 22:
Week 15 (April 27, 29)
April 27:
April 29:

Grading

All graded work will receive a grade, 4.0, 3.7, 3.3, 3.0, 2.7, 2.3, 2.0, 1.7, 1.3, 1.0, or 0.0. At the end of the semester, final grades will be calculated as a weighted average of all grades.