Downloads for CIspace

This is the downloads page for CIspace, where the user can download the CIspace programs. They can be run as either applications and applets from the jars. Win32 executables are also provided.

Instructions

Extract the zip file. After extracting, make sure that the unzipping utility created a /saves folder.

For the jar files

To run the program as an applet, find the applet html file in the program directory. For example, the Neural Networks zip file will have a neural.html file in the directory the user extracted it to. Open this file with a browser.
To run the program as an application (recommended for speed reasons), the user must have Java 1.2 or later installed. This can be acquired from Sun's Java website. Go to the program's directory, and run the application by typing java -jar appname.jar. For example, to run the Robot Control program, type java -jar robot.jar.

For the Win32 executables

To run the executable, open the .exe file.

Version 4.0

	Definite Clause Deduction Every representation and reasoning system needs a proof procedure in order to be complete. The purpose of this applet is to illustrate how the process of answer extraction within a knowledge base can be cast as a search problem. The deduction applet uses a language similar to Prolog and demonstrates its goal solving procedures. [Download the .jar] [Download the Win32 executable]
	Graph Searching Search is an important part of CI; many problems can be cast as the problem of finding a path in a graph. This graph-searching applet is designed to help you learn about different search strategies. [Download the .jar] [Download the Win32 executable]
	Consistency Based CSP Solver Constraint satisfaction problems (CSPs) are pervasive in AI problems. A constraint satisfaction problem is the problem of assigning values to variables that satisfy some constraints. This applet lets you investigate arc consistency and domain splitting with backtracking as ways to solve these problems. [Download the .jar] [Download the Win32 executable]
	Stochastic Local Search for CSPs This applet is designed to help you learn another strategy for solving CSPs. This applet demonstrates stochastic local search (various mixes of hill climbing and random moves) that walks through the space of total assignments trying to find an assignment with minimal error. [Download the .jar] [Download the Win32 executable]
	Planning Planning is essential for agents that act in an environment. To solve a goal intelligently, an agent needs to think about what it will do now and in the future. This applet demonstrates planning using the blockworld problem domain and STRIPS representation. [Download the .jar] [Download the Win32 executable]
	Decision Trees Learning is the ability to improve one's behaviour based on experience and represents an important element of computational intelligence. Decision trees are a simple yet successful technique for supervised classification learning. This applet demonstrates how to build a decision tree using a training data set and then use the tree to classify unseen examples in a test data set. [Download the .jar] [Download the Win32 executable]
	Robot Control A robot is an intelligent agent that perceives, reasons, and acts in time in an environment. It acts to achieve its assigned goals and at the same time avoids getting into undesired states. The robot applet provides a simulation of a robot perceiving and acting under the control of a set of customizable robot controller functions. [Download the .jar] [Download the Win32 executable]

Version 3.0

	Belief and Decision Networks Belief networks (also called Bayesian networks or causal networks) are a representation for independence amongst random variables for probabilistic reasoning under uncertainty. The purpose of this applet is to illustrate how probabilities are updated given new evidence in a belief network, and shows the details of how the variable elimination algorithm works. [Download the .jar] [Download the Win32 executable]
	Neural Networks Inspired by neurons and their connections in the brain, neural networks are a representation used in machine learning. After running the back-propagation learning algorithm on a given set of examples, the neural network can be used to predict outcomes for any set of input values. [Download the .jar] [Download the Win32 executable]
	These applets were designed and written by Mike Cline, Wesley Coelho, Kevin O'Neill, Mike Pavlin, Joseph Roy Santos, Shinjiro Sueda, Leslie Tung, and Audrey Yap, under the guidance of Cristina Conati, Peter Gorniak, Holger Hoos, Alan Mackworth, and David Poole. Copyright © 1999, 2000, 2001, 2002 M. Cline, W. Coelho, C. Conati, P. Gorniak, H. Hoos, A. Mackworth, K. O'Neill, M. Pavlin, J. Santos, D. Poole, S. Sueda, L. Tung, and A. Yap. For questions about the overall CIspace project please contact Alan Mackworth or David Poole.

If you have any questions or comments about this website or any of the applets please email ci-space@cs.ubc.ca

Last Updated: October 6th, 2003