New Bulgarian University >

Center for Cognitive Science >

Summer Schools >

2004 >

Course Description

 

 

 

Adaptive Individuals in Evolving Populations

 

Richard K. Belew

 

 

This course will first introduce techniques of  evolutionary computation (also know as genetic algorithms) as models of evolving populations for use in cognitive science. It will then explore new questions arising as these models are combined with connectionist models of individual learning and grammatical models of maturation (growth).  Finally, the approach will be applied to construction and control of artificial robots.

 

Primary text: An Introduction to Genetic Algorithms (Complex Adaptive Systems)
by Melanie Mitchell
MIT Press, 1999
ISBN: 0262631857

 

 

Day 1: Introduction to the evolutionary approach

 

Required readings:

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 1.9

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 1.1-1.6

 

Lab session: Python

 

 

Day 2: Representations & operators

 

Required readings:

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 5.2,5.3

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 5.4-5.6

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 3.2-3.4

 

Lab session: Basic Evolutionary Computation

 

 

Day 3: Evolution & learning

 

Required readings:

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 3.1

Melanie Mitchell.  An Introduction to Genetic Algorithms (Complex Adaptive Systems), 2.3,

Optional readings:

I. Harvey. The Puzzle of the Persistent Question Marks: A Case Study of Genetic Drift   

 

Lab session: Role of CrossOver

 

 

Day 4: Evolution & Maturation

 

Required readings:

F. Cecconi, F. Menczer, R. Belew. Maturation and evolution of imitative learning in artificial organisms   

 

Optional readings:

P. Todd, G. Miller. Parental guidance suggested: How parental imprinting evolves through sexual selection as an adaptive learning mechanism   

 

Lab session: Evolving functions

 

 

Day 5: Evolving robotic designs

 

Required readings:

C. Mauter, R. Belew. Evolving Robot Morphology and Control

 

Optional readings:

G. Hornby, J. Pollacj. Creating High-level Components with a Generative Representation for Body-Brain Evolution

 

Lab session: Evolving functions II

 

Assessment:

 

           Lab sessions will explore simple implementations of evolutionary algorithms in Python.  Students wishing to take the course for credit are expected to participate in these lab sessions.

 

Richard Belew

 

Richard K. Belew is a professor of  Cognitive Science at The University of California, San Diego.  His research focuses on adaptive knowledge representation,  particularly the integration of induced knowledge with traditional scientific publication and data.  He is author of Finding Out About (Cambridge Univ. Press, 2000) and co-editor (with Melanie Mitchell) of Adaptive Individuals in Populations (Addison-Wesley, 1996). He received his PhD from  the Unviersity of Michigan..