CMU Artificial Intelligence Repository
Home INFO Search FAQs Repository Root

ML-Code: Lisp Code for Assignments in Mooney's Machine Learning Course

This directory contains a copy of the Common Lisp code corresponding to the assignments for the graduate course in machine learning taught by Dr. Mooney. The programs include: 1. AQ algorithms for learning from examples. Uses either beam search with bounded stars or the version space algorithm to compute stars. 2. BACKPROP. 3. COBWEB. Incremental conceptual clustering algorithm (with soybean data). 4. DEDUCE. Prolog-like theorem prover or deductive retrieval system. Uses generators to retrieve one answer at a time and also generates proofs. Supports only backward chaining, with optional depth bound on the number of rules. 5. EGGS. Explanation-Based Generalizer. EGGS can generalize the proofs returned by DEDUCE and generate macro-rules from the general proofs. These macro-rules are stored and preferentially used in future deductions to increase performance. 6. EXPLORER. In the spirit of AM, but more limited. Explores a space of concepts, guided by "interestingness" measures and makes conjectures about the concepts it explores. 7. ID3 algorithm for learning from examples. Produces decision trees discriminating positive and negative instances. 8. PERCEPTRON. Simple system for learning from examples using the perceptron learning procedure to adjust a set of weights on a single linear threshold unit until all of the training examples are correctly classified. 9. VERSION-SPACE algorithm for incremental learning from examples.

Requires: Common Lisp Copying: Copyright (c) 1991 by Raymond J. Mooney Use permitted for educational and research purposes only. Users are requested, but not required, to inform Raymond J. Mooney of any noteworthy uses of this software. Please see the file readme.txt for details. CD-ROM: Prime Time Freeware for AI, Issue 1-1 Author(s): Raymond J. Mooney, Jude W. Shavlik Contact: Raymond J. Mooney Assistant Professor Department of Computer Sciences University of Texas at Austin Keywords: AM, AQ, Authors!Mooney, Authors!Shavlik, Backpropagation, Backward Chaining, COBWEB, Clustering, DEDUCE, Decision Trees, Deductive Retrieval, EBG, EGGS, EXPLORER, ID3, Incremental Conceptual Clustering, Incremental Learning, Inductive Classification, Learning from Examples, Lisp!Code, Machine Learning, Perceptrons, Teaching Materials, Theorem Proving, Version Spaces References: ?
Last Web update on Mon Feb 13 10:24:34 1995