Artificial Minds and Simulated Bodies
Speaker: Sergei Nirenbrg
Department of Cognitive Science and Computer Science, RPI
September 30, 2014 - 4:00 p.m. to 5:00 p.m.
Location: CII (Low) 3051
Hosted By: Dr. Peter Fox (x4862)
Our research group develops artificial intelligent agents capable of perception, decision making, language understanding, mental and verbal action and learning. They are distinguished by having different knowledge about the world and about language and by differences in personal characteristics and biases. Reasoning and decision making tasks are formulated using the knowledge substrate originally developed for OntoSem, our ontological-semantic language processing system.
In this talk I will describe two proof-of-concept applications of our approach to intelligent agency, both in the domain of clinical medicine.
MVP is a training environment in which a human trainee plays the role of attending physician while artificial agents play the roles of the patient, tutor and supporting medical personnel. Our virtual patients are “double agents” in that both their bodies and their minds are modeled. Specifically, they are endowed with a) simulated physiology that tracks the progression of a disease and responds appropriately to external medical interventions; and b) a model of the mind, manifesting itself in the patient’s ability to initiate action as well as remember, understand and dynamically react to textual input, and learn through experience.
In the CLAD environment the artificial agent gives advice to a clinician during an interview with a human patient. This advisor agent is purely cognitive (that is, its body is not modeled) but it develops and manipulates a mental model of both the mind and the body of the human patient. A core prerequisite of generating high-quality advice is CLAD’s ability to simulate the expected progression of each specific patient’s disease, based on information already gathered about him or her, and to predict the patient’s likely responses to different treatment options.
Sergei Nirenburg is Professor of Cognitive Science and Professor of Computer Science at Rensselaer Polytechnic Institute. He has worked in the areas of cognitive science, artificial intelligence and natural language processing (NLP) for over 35 years, leading R&D teams of up to 80. His professional interests range over a broad range of topics related to developing computational models of human cognitive capabilities and implementing them in hybrid-engine models of societies of human and language-endowed artificial intelligent agents. Dr. Nirenburg received a M.Sc. in Computational Linguistics from Kharkov State University, USSR (1974) and a PhD in Linguistics from The Hebrew University of Jerusalem, Israel (1980). Before coming to RPI he taught in the Computer Science departments at the Hebrew University, Colgate University, Carnegie Mellon University, New Mexico State University and University of Maryland Baltimore County. In 1994-2002 he was Director of New Mexico University’s Computing Research Laboratory, a major AI and NLP research institute. Dr. Nirenburg has written two and edited five books and published over 190 scholarly articles in journals and peer-reviewed conference proceedings. He is Member of the International Committee on Computational Linguistics and Honorary Editor of Machine Translation, the archival scholarly journal, which he served as Editor-in-Chief in 1987-96.
Last updated: August 14, 2014