Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Portland State University

Robotics

Artificial intelligence

Articles 1 - 2 of 2

Full-Text Articles in Engineering

Evolving Machine Morality Strategies Through Multiagent Simulations, David Burke Jun 2011

Evolving Machine Morality Strategies Through Multiagent Simulations, David Burke

Systems Science Friday Noon Seminar Series

There is a general consensus among robotics researchers that the world of the future will be filled with autonomous and semi-autonomous machines. There is less of a consensus, though, on the best approach to instilling a sense of 'machine morality' in these systems so that they will be able to have effective interactions with humans in an increasingly complex world. In my talk, we take a brief look at some existing approaches to computational ethics, and then describe work we've undertaken creating multiagent simulations involving moral decision-making during strategic interactions. In these simulations, agents make choices about whether to cooperate …


Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson Mar 1999

Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson

Electrical and Computer Engineering Faculty Publications and Presentations

"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only.