I400/I590 Artificial Life as an approach to Artificial Intelligence

Spring Semester 2007

 

Professor:  Larry Yaeger

Office: Eigenmann Hall, Rm 907 (South wing)

Office Hours:  By appointment, any afternoon or early evening I'm not in a class or meeting; see my work calendar

Phone:  (812) 856-1845

Email:  larryy (at) indiana.edu

 

Meeting Times:  2:30pm – 3:45pm MW                     Location: Informatics Bldg, Rm I107

 

Textbook (required): Braitenberg, V. Vehicles: Experiments in Synthetic Psychology

All other reading materials available online via links on this page (on the private site only).

 

NOTE: This document appears in both a public and a private place; reading material links only work on the private site, to abide by copyright restrictions.  (Lecture note links work on both sites.)  The private site’s URL is provided to enrolled students and is accessible via OnCourse.

 

Schedule and Reading List

 

Links under the “Topics” heading are to PowerPoint lecture notes.  You can download these in advance if you want something to take notes on, but be warned, they are likely to be in flux until the day of the class.

 

In the topics, S# means Speaker #.  (Speaker topics can be inferred from the schedule, but are listed explicitly at the bottom of this page.)

In the reading assignments, B# means chapter # of the Braitenberg book.

L# is Lecture #.

 

Class

Date

Topics

Reading Assignment (for next class)

Extras (not required)

 1a

MO  8 Jan

Class intro, L1-Intro to Artificial Life

Langton1

Dyson

 1b

WE 10 Jan

Intro to Braitenberg, L2-Is it alive?

Farmer & Belin, B1

 

  

MO 15 Jan

No class - MLK Holiday

 

 

 2b

WE 17 Jan

S1 (WillP), B1, L3-Intro to GAs

Goldberg, B2

Holland, Fraser, Charbonneau

 3a

MO 22 Jan

S2 (DavidR, DianeC), B2, discussion

 

 

 3b

WE 24 Jan

L4-Simulated Evolution (Sims movie)

Ray, Sims, B3

Sims1, Sims2

 4a

MO 29 Jan

S3 (JaredS, JeremyT), B3, discussion, test prep

Exam 1, take-home

 

 4b

WE 31 Feb

Exam 1 due, L5-Neural Networks Pt. 1 - Terms & Defs

Anderson, B4

Rumelhart & McClelland

 5a

MO  5 Feb

Return exams, S4 (JoshuaM), B4, discussion

 

 

 5b

WE  7 Feb

L6-Neural Nets Pt. 2 - Association & Hebb

James, Hebb, B5

Plasticity

 6a

MO 12 Feb

S5 (NateS, StephenD), Mitja Hmeljack on Second Life, discussion

 

 

 6b

WE 14 Feb

B5, L7-Intro to Information Theory

Schneider, B6

Shannon, n-grams

 7a

MO 19 Feb

John Beggs guest lecture

 

 

 7b

WE 21 Feb

L8-Neural Nets Pt 3 – Hebbian learning via Information Theory

Linsker1, Linsker2, B7

Swindale

 8a

MO 26 Feb

S6 (PaulW),  S7 (MattZ), B6, B7, test prep

 

 

 8b

WE 28 Feb

In-class Midterm (Exam 2)

B8

 

 9a

MO  5 Mar

Return and discuss exams, S8 (no one), B8, discussion

 

 

 9b

WE  7 Mar

L9-Neural Nets Pt 4 – Spiking Neuron Models

Izhikevich1, Izhikevich2, Izhikevich3

Herz, Destexhe, O'Reilly

  

MO 12 Mar

No Class - Spring Break

 

 

  

WE 14 Mar

No Class - Spring Break

 

 

10a

MO 19 Mar

Informal presentation of project ideas

 

 

10b

WE 21 Mar

L10-Evolution & Learning

Hinton&Nowlan, Parisi, Chalmers, B9

Belew

11a

MO 26 Mar

Olaf Sporns guest lecture

 

Tononi1, Buzsáki

11b

WE 28 Mar

L11-Organisms simulated and real (Koko, Dolphin, Betty, Alex)

Walter, NewSci, Salience, Giurfa, B10

Swinderen, Foote

12a

MO  2 Apr

S9 (RickH), S10 (WillY), B9, B10, discussion

 

 

12b

WE  4 Apr

L12-Intelligence as an Emergent Phenomenon

Hillis, B11

Dennett

13a

MO  9 Apr

S11 (OliverM, DrewH), B11, discussion, test prep

Exam 3, take-home

 

13b

WE 11 Apr

Exam 3 due, L13-Evolution of Intelligence (movies)

Yaeger, B12

Gould, McShea

14a

MO 16 Apr

Return exams, S12 (no one), B12, discussion

 

 

14b

WE 18 Apr

L14-Is it alive? Pt. 2, Measuring Complexity

Langton2, B13, B14

Crutchfield, Feldman, Tononi2

15a

MO 23 Apr

Projects due, S13 (MikeR), B13, B14, Project Demos

 

 

15b

WE 25 Apr

Project Demos, Discussion and review for final exam

 

 

  

MO 30 Apr

Final Exam 2:45pm - 4:45pm (Exam 4)

 

 


Requirements

 

Students will be expected to attend class, do weekly readings, and participate in discussions.  In addition, each student will present and lead a discussion on the material in one topic area, and will do one of the following:

 

Š      Write a final paper (grads 20-25 pages, undergrads 15-20 pages) demonstrating insight into one of the topic areas.

Š      Write a functioning ALife simulator of at least modest complexity (more than just a simple CA or Conway Game of Life; student should consult with teacher before writing).

Š      Turn in a technical paper describing the results of an ALife experiment, carried out with Tierra, Avida, Swarm, PolyWorld, or other ALife software (student may consult with teacher in selection of software and topic).

 

There will be four exams—two take-home exams, an in-class midterm, and an in-class final exam.  The lowest test grade will be dropped, thus the final is optional, if a student is satisfied with the first three test results.  The midterm and particularly the final may include cumulative questions, but will primarily focus on the material since the last test.  Dates are indicated in the schedule above.

 

Course Structure

 

Generally, each week’s theme will bridge weekends, being introduced by me in the WE lecture class, and then followed up with readings before the next class on MO, in order to allow students maximum time to read and prepare for discussion.  On the following MO, student presentations of a topic related to the reading materials will take place, followed by a discussion of one of the chapters from the Braitenberg book, followed by any additional material I need to communicate, and class discussion of that week’s topic.  (There will be exceptions to this pattern, as indicated in the above schedule, at the start of the semester and around Spring Break.)

 

Each student will prepare one presentation during the semester on a topic related to the reading materials.  We will agree on and set dates in the first class.  If there are more than 13 students in the class, we will fit extra presentations in as needed.  These presentations are to be 15 to 20 minutes only.  In general, I hope students will select one of the papers referenced by the primary reading material and use that as the basis for their presentation.  But if there is a topic of particular interest to a student in the reading material itself and I have not covered that topic in the lecture class, that will be acceptable.  Related papers not taken from the reference list may also be acceptable, but require my approval.

 

Each student will also work on one final project.  As indicated above, this project may take the form of writing your own ALife simulator, performing experiments with an existing ALife simulator, or researching and writing on a topic in the field, in order to accommodate all computer skill levels.  Projects will be due on Monday 25 April, 2005.

 

Grading

 

Each of the four tests, class participation, the topic presentation, and the final project will contribute to the total grade as follows:

 

Participation

5 pts

(Yes, it really does count)

Gedanken experiment

5 pts

 

Presentation

10 pts

 

Project

20 pts

 

 

 

 

Test 1 (take-home)

20 pts

 

Test 2 - Midterm

20 pts

 

Test 3 (take-home)

20 pts

 

Test 4 - Final

20 pts

 

 

 

 

Total

120 pts

(100 pts after dropping the lowest test score)

 

The extended gedanken experiment will be defined in the first week.  This experiment will pose a challenge that, if answered correctly by anyone in the class, anytime before the end of the semester, will result in the credit being received by the entire class.

 

Grades will not be curved and will be assigned as follows (this is the same as used in I101 and I210, but differs from some other classes):

 

A+

98-100

4.0

A

93-97

4.0

A-

90-92

3.7

B+

85-89

3.3

B

80-84

3.0

B-

75-79

2.7

C+

70-74

2.3

C

65-69

2.0

C-

60-64

1.7

D+

55-59

1.3

D

50-54

1.0

D-

45-49

0.7

F

  0-44

0.0

 

Conduct

 

Cooperation on the extra credit problem is encouraged, as is discussion in general.  In fact, I intend to set up an email list to facilitate discussions outside of class.  However, tests must be taken individually, both take-home and in-class.  Cheating will be reported according to university policies.

 

General Course Description

 

Artificial Life is a broad discipline encompassing the origins, modeling, and synthesis of natural and artificial living entities and systems.  Artificial Intelligence, as a discipline, tries to model and understand intelligent systems and behavior, typically at the human level.  This class will introduce core concepts and technologies employed in Artificial Life systems that can be used to approach the evolution of Artificial Intelligence in computers.  Key themes include:

 

- bottom-up design and synthesis principles,

- definitions and measurements of life and intelligence,

- genetic algorithms,

- neural networks,

- the evolution of learning,

- the emergence of intelligence,

- computational ecologies, and

- information theory-based measures of complexity.

 

Our path through these materials will lay the theoretical groundwork for an approach to Artificial Intelligence based on the tenets and practices of Artificial Life—an approach which utilizes evolution to start small and work our way up a spectrum of intelligence, from the simplest organisms to the most complex, rather than attempting to model human-level intelligence from the outset.

 

Lectures and readings will be based on seminal papers and introductory texts in these fields, drawing from the Artificial Life conference proceedings, and technical papers by Donald Hebb (from which we obtain Hebbian learning), Rumelhart and McClelland (editors of and authors in the original Parallel Distributed Processing books that launched the modern neural network field), Ralph Linsker ("Infomax" theoretical approach to neural network learning), Hinton and Nowland (the "Baldwin effect"), William James ("the greatest American psychologist"), W. Grey Walter, Tom Ray, Karl Sims, Danny Hillis, and others.  We will also read and discuss Braitenberg's seductive and influential Vehicles book.

 

References

 

Anderson, J. A., General Introduction, p. xiii-xxi, Neurcomputing, Foundations of Research, ed. by J. A. Anderson and E. Rosenfeld, A Bradford Book, MIT Press, Cambridge, Massachusetts, 1988

                                                                                          

Chalmers, D., "The Evolution of Learning: An Experiment in Genetic Connectionism" in Connectionist Models, Proceedings of the 1990 Summer School, edited by D. S. Touretzky, J. L. Elman, T. J. Sejnowski, G. E. Hinton, Morgan Kaufmann, San Mateo, CA, 1991

                                                                                                                           

Douglas, F., “Do fruit flies dream of electric bananas?”, New Scientist, 14 February 2004

                                                                                                                  

Farmer, J. D., and A. d’A. Belin, "Artificial Life: The Coming Evolution"  In Artificial Life II, edited by C. Langton, C. Taylor, J. Farmer, and S. Rasmussen.  Proceedings of the Artificial Life II Conference (in 1990), Santa Fe Institute Studies in the Sciences of Complexity Proc. Vol. X.  Addison-Wesley, Redwood City, CA, 1992

                                                                                                              

Frye, M.A. & Dickinson, M.H. “A signature of salience in the Drosophila brain”, commentary on article by Swinderen & Greenspan, Nat. Neur. 6 (6) 544-546 June 2003

                                                                                                                 

Giurfa, M., Zhang, S., Jenett, A., Menzel, R., Mandyam, V., “The concepts of 'sameness' and 'difference' in an insect”, Nature 410(6831) 930-933, 19 Apr 2001

                                                                                                                  

Goldberg, D. E., A Gentle Introduction to Genetic Algorithms, p. 1-23, Chapter 1 of Genetic Algorithms in Search, Optimization, and Machine Learning, by D. E. Goldberg, Addison-Wesley 1989

                                                                                                                    

Hebb, D. O., Introduction (p. xi-xix) and Chapter 4, "The first stage of perception: growth of the assembly" (p. 60-78), The Organization of Behavior, Wiley, New York, 1949 (with introduction, p. 43-56 from Neurocomputing, Foundations of Research, ed. by J. A. Anderson and E. Rosenfeld, A Bradford Book, MIT Press, Cambridge, Massachusetts, 1988)

                                                                                                                       

Hillis, D. W., Intelligence as an Emergent Behavior, p. 175-189, Daedalus, Journal of the American Academy of Arts and Sciences, special issue on Artificial Intelligence, Winter 1988

                                                                                                                      

Hinton, G. E. and Nowlan, S. J., How learning can guide evolution. Complex Systems, 1:495--502, 1987

                                                                                                                         

Izhikevich, Eugene M., Simple Model of Spiking Neurons, IEEE Transactions on Neural Networks (2003) 14:1569-1572

http://www.nsi.edu/users/izhikevich/publications/spikes.htm

                                                                                                                            

Izhikevich, Eugene M., Which Model to Use for Cortical Spiking Neurons? IEEE Transactions on Neural Networks (2004) 15:1063-1070

http://www.nsi.edu/users/izhikevich/publications/whichmod.htm

                                                                                                                                

Izhikevich, Eugene M., Polychronization: Computation With Spikes, Neural Computation (2006) 18:245-28

http://www.nsi.edu/users/izhikevich/publications/spnet.htm                                            

                                                                    

James, W., Association, Chapter XVI of Psychology (Briefer Course), p. 253-279, Holt, New York, 1890 (with introduction, p. 1-14 from Neurocomputing, Foundations of Research, ed. by J. A. Anderson and E. Rosenfeld, A Bradford Book, MIT Press, Cambridge, Massachusetts, 1988)

                                                                       

Langton, C. G., Artificial Life, preface to Artificial Life, The Proceedings of an Interdisciplinary Workshop on the Synthesis and Simulation of Living Systems held September, 1987 in Los Alamos, New Mexico, Santa Fe Institute Studies in the Sciences of Complexity Proc. Vol. VI., edited by C. Langton, Addison Wesley, Redwood City, CA, 1989

                                                                     

Langton, C. G., Computation at the Edge of Chaos: Phase Transitions and Emergent Computation, p. 12-37, Emergent Computation, Proceedings of the Ninth Annual International Conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks, Los Alamos, NM, 1989, ed. Stephanie Forrest, North Holland, 1990

                                                                          

Linsker, R., "Towards an Organizing Principle for a Layered Perceptual Network" in Neural Information Processing Systems, ed. by D. Z. Anderson. American Institute of Physics, New York, 1988

                                                                              

Linsker, R., "Self-Organization in a Perceptual Network", Computer 21(3), 105-117, March 1988

                                                                              

Parisi, D., S. Nolfi, and F. Cecconi, "Learning, Behavior, and Evolution", Tech. Rep. PCIA-91-14, Dept. of Cognitive Processes and Artificial Intelligence, Institute of Psychology, C.N.R., Rome, June 1991. (Appeared in Proceedings of ECAL-91—First European Conference on Artificial Life, December 1991, Paris; also in Varela, F, Bourgine, P. Toward a pratice of autonomous systems. MIT Press. 1991

                                                                              

Ray, T. S. 1992. Evolution, ecology and optimization of digital organisms. Santa Fe Institute working paper 92-08-042

                                                                                     

Rumelhart, D. E. and McClelland, J. L., PDP Models and General Issues of Cognitive Science, p. 110-146, Chapter 4 of Parallel Distributed Processing, Explorations in the Microstructure of Cognition, Volume 1: Foundations, ed. by D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, A Bradford Book, MIT Press, Cambridge, Massachusetts, 1986

                                                                                      

Schneider, T., “Information Theory Primer”, <http://www.lecb.ncifcrf.gov/~toms/paper/primer/>

                                                                                            

Sims, K., Evolving Virtual Creatures, Computer Graphics, Annual Conference Series, (SIGGRAPH ‘94 Proceedings), July 1994, pp.15-22.

                                                                                              

Walter, W. G. (1950), "An Imitation of Life", Scientific American, 182(5), 42-45, May 1950

                                                                                                    

Yaeger, L. S., Computational Genetics, Physiology, Metabolism, Neural Systems, Learning, Vision, and Behavior or PolyWorld: Life in a New Context, p. 263-298, Proceedings of the Artificial Life III Conference (in 1992), ed. Chris Langton, Addison-Wesley, 1994

 

Speaker Topics

 

S1 – Intro to Artificial Life or Is It Alive?

S2 – Genetic Algorithms

S3 – Simulated Evolution

S4 – Neural Networks, Intro

S5 – Neural Networks, Association & Hebb

S6 – Information Theory

S7 – Neural Networks, Information theoretic approach to neural network learning

S8 – Any of the above!

S9 – Combining evolution and learning

S10 – Animal intelligence, intelligence in simulated organisms

S11 – Intelligence as an emergent phenomenon

S12 – Evolution of intelligence

S13 – Complexity

 

Links to previous student presentations may be found on the following class home pages from previous semesters.  Click on the student's name in parentheses to download the presentation.  If the "S#" indicator is also a link, then it will point to supporting materials for the presentation.  (Other links on these pages do not work.)

 

Spring 2005

Fall 2005

 

Look here for examples of previous semester projects.