An Algorithmic and Social Introduction to Computer Science (CSC-105 2000S)


Class 39: AI Experiments

Back to Genetic Algorithms. On to Evaluating AI.

Held Wednesday, April 12, 2000

Overview

Today we will play with and discuss some of the sample neural networks you've identified.

Question 39 for discussion today: Find a Web site with an illustrative example of genetic programming or neural networks. Report on the success or failure of the technique to solve the problem described therein.

Question 40 for discussion Friday: Do you consider the Turing test a reasonable way to evaluate the the success of an AI program? Why or why not?

Notes

Contents

Summary


Investigations

We'll start by looking at a simple (but, presumably, general) neural network designed for doing function approximation. You can find this at http://neuron.eng.wayne.edu/bpFunctionApprox/bpFunctionApprox.html.

Spend a little time playing with the applet. What do you discover? Note that you may need to resize some dialog boxes in order to get it to work. Note also that it may take some time to load.

We'll continue with some of the examples you've come up with. See your answers to today's question for the examples.


History

Saturday, 22 January 2000

Wednesday, 12 April 2000

Back to Genetic Algorithms. On to Evaluating AI.


Disclaimer Often, these pages were created "on the fly" with little, if any, proofreading. Any or all of the information on the pages may be incorrect. Please contact me if you notice errors.

This page may be found at http://www.math.grin.edu/~rebelsky/Courses/CS105/2000S/Outlines/outline.39.html

Source text last modified Wed Apr 12 09:51:12 2000.

This page generated on Wed Apr 12 09:54:28 2000 by Siteweaver. Validate this page's HTML.

Contact our webmaster at rebelsky@grinnell.edu