University of Maryland Department of Computer Science

James A. Reggia

Current Positions:

Research Interests

Our research group focuses on studying and understanding 1) the underlying principles of biological computation, and how these principles can be adopted or modified to extend contemporary computer science methods, and 2) automated causal reasoning, such as abductive inference and Bayesian/belief networks.

Several properties of biologically-inspired computing separate it from more traditional computer science, giving hope that new robust and adaptive software methods can be developed. Examples of this type of computing include neural computation, evolutionary computation, artificial life, self-replicating machines, artificial immune systems, ant colony optimization, L-systems, artificial societies, and swarm intelligence. Our group has worked and/or is working in the following areas:

We are also focusing on automated causal reasoning using more traditional methods in artificial intelligence. The goal of this research is to model human cognition as a means of generating useful automated reasoning systems. Our group has worked and/or is working in the following areas:

We have an active seminar schedule that is open to interested individuals, and a recent undergraduate GEMSTONE research group working on genetic programming and multi-agent systems. Some simple online demonstrations illustrate a simulated self-assembling building , a neural model of cortical spreading depression, a a collection of cellular automata self-replicating structures, that were discovered using genetic programming, and a cellular automata model of self-replicating "machines" rendered with chess pieces.

Imitation Learning by Cognitive Robots

We are studying methods for imitation learning by bimanual robots as part of an ONR-supported project.

Upcoming/Recently Taught Courses

CMSC 289I: Rise of the Machines - Fall 2016
CMSC 389F: Reinforcement Learning (advisor) - Fall 2018
CMSC 421: Introduction to Artificial Intelligence - Spring 2018
CMSC 422: Introduction to Machine Learning - Spring 2019
CMSC 726: Machine Learning
CMSC 727: Neural Computation - Fall 2018
CMSC 828Q: Nature-Inspired Computing - Fall 2019

Past NSF Projects

We developed methods for self-organizing collective intelligence for adaptive problem solving as part of an NSF ITR project.

We also studied methods for computer-supported creativity enhancement using evolutionary computation as part of an NSF CreativeIT project.