Gregory D. Weber
Associate Professor Emeritus of Computer Science and Informatics
(RETIRED since May, 2017)
Indiana University East
| Contact | Courses | Research | Home pages |
| Contact | Courses | Research | Home pages |
Revised 2026 June 16, 14:45 EDT
I am in the process of migrating these pages to https://gdweber.org.
Abstract: Sifflet is a visual, functional programming language and environment, developed as an aid for understanding recursive functions. Sifflet's explanations of recursive computations provide visual reinforcement of the copies model of recursion. They are driven by student demand, supporting active learning and avoiding information overload.
Copyright 2013 by the Consortium for Computing Sciences in Colleges, reproduced with permission.
Citation in ACM Digital Library.
Abstract: This paper describes the author's experience of using the programming language Mercury to re-implement the machine learning program CN2. Mercury is a purely declarative language, closely related to Prolog, and designed for speed.
Abstract: This paper describes ICN, an incremental version of the CN2 rule learning system. Unlike other incremental rule learning systems which learn rules gradually, adding and removing conditions in a hill-climbing search, ICN learns or unlearns each rule "all at once," using beam search as in CN2. In batch training and testing with the forest cover prediction problem, ICN performs nearly as well as CN2. ICN's efficient incremental algorithm, however, allows it to learn from much more data. When trained and tested incrementally on the entire forest cover data set (581,012 instances), ICN's performance exceeds that of the best known classifier for this problem.
Abstract: This paper describes PISCES, a system for incremental learning of probabilistic rules. PISCES is efficiently incremental in the sense that both its processing time per instance and its memory usage are independent of the number of training instances. Classification accuracy alone does not provide a sufficient measure of performance for probabilistic classifiers. Additional measures include extrinsic confidence (EC), which is the average degree to which actual events are unsurprising; and intrinsic confidence (IC) and entropy, which measure certainty. EC and IC are also useful as heuristic functions in the search for concept descriptions. PISCES achieves classification accuracy nearly as high as that of a non-incremental rule learning system, and significantly better performance according to the other three measures.
Abstract:
Brickworld is a simulated environment which has been developed as a testbed for learning and planning—in particular, for learning and using knowledge of causal relations. The environment is both dynamic—there are other "agents" whose actions affect "the" agent's performance—and stochastic—future states can be predicted only with uncertainty. The task, building and maintaining a wall, has been formulated as a reinforcement learning problem. The ultimate goal of the Brickworld project is to develop a relational reinforcement learning agent that will learn a causal model of the environment representing both its own causal powers and those of the other "agents." The term "agents" is used here in the broadest possible sense, including not only intelligent agents but brute animals and even natural forces such as wind and rain—anything that can be a cause of environmental change.
This paper describes seven implemented agents—a quasi-reactive agent, four non-learning rule-based agents, and two (non-relational) reinforcement learning agents—and compares their performance. The experiments show that a reasonable knowledge representation for the environment results in a state-value function which has local optima, making greedy and epsilon-greedy policies inappropriate. Deeper search is required, leading to problems of inefficiency, which may be alleviated through hierarchical problem spaces. The paper raises questions about the legitimacy of programmer-designed hierarchies in the framework of reinforcement learning and suggests a principled solution.