Machines that Read, Learn, and Reason

The School of Sciences, UCLan Cyprus cordially invites you to a seminar titled:

“Machines that Read, Learn, and Reason”

with a guest talk from Assistant Professor Loizos Michael (Open University of Cyprus).

Abstract

In seeking to build intelligent machines, one could consider endowing them with functionality analogous to what is present in human cognition, such as the ability to learn through experiences, and the ability to reason with knowledge. The experiences through which humans learn knowledge are readily available through their sensors and as a result of the multifaceted and lengthy interaction with their environment. Until the development of machines able to equally easily roam and interact with their environment for extended periods of time, an alternative source of learning experiences would seem to be needed for machines. The Web can readily play the role of this alternative source, assuming that machines are able to process natural language text. We will present work towards developing machines designed to exploit Web-extracted experiences, aiming to learn what could be called websense knowledge. Knowledge of this type is not encoded explicitly in individual web-pages, but is consistent with information commonly found across web-pages. It could be argued that websense captures certain aspects of the actual human environment, and could form the basis for endowing machines with commonsense-like knowledge.

---

Loizos Michael is an Assistant Professor at Open University of Cyprus, where he founded and directs the Computational Cognition Lab. He was educated at University of Cyprus, receiving a B.Sc. in Computer Science with a minor degree in Mathematics. He continued his education at Harvard University, where he received an M.Sc. and a Ph.D. in Computer Science. His research focuses on the principled study of cognitive processes associated with individual or collective intelligence — such as learning, reasoning, sensing, communication, cooperation — and how those are employed by humans and other organisms. Emphasis is placed on the development of computational models for various aspects of cognitive processes, and the analysis of the formal implications that such models have. This computational view of cognition is complemented by simulations, real-world experiments, and psychological studies, designed to validate the proposed models and to identify features thereof that warrant further study.

---

When: Wednesday, February 19th, 2013 at 14:00-15:00

Where: Room CY115 (First floor), UCLan Cyprus, Pyla CY-7080