Seminar by Roger Kingdon
A review of cognitive architectures
Roger Kingdon
Dstl, Oxford, United Kingdom
Date: Monday, November 9, 2009
Time: 10:00 AM
Venue: CS103.
Abstract:
This talk presents a paper which extends Vernon, Metta and Sandini's review of cognitive architectures by reassessing the designs against five new 'structural' criteria. This approach involves analysing the flowchart representation of each architecture to establish: whether its modules are well-defined; whether its internal connections are suitable; whether there is a double loop for higher-level processing; whether the architecture has been demonstrated in a practical application; and whether its modules map to the main regions of the human brain. By these criteria, the architectures judged to have the greatest promise are ACT-R, Global Workspace, and SOAR. It is acknowledged, however, that none of the reviewed architectures fully address the last criterion in the above list; and this establishes the need for a broader survey, to include more novel but less-established alternative designs.
About The Speaker:
Roger Kingdon is a computational physicist with over 20 years of postdoctoral experience in the theory and modelling of a wide range of physical systems using both conventional and novel techniques. He has 28 publications in the open literature and he is a named author on 47 other unclassified reports. In addition he has have maintained a strong spare-time interest in artificial intelligence which has resulted in the development of a novel cognitive architecture known as 'IDEAL', and a book, 'Principia Intellegentia: The principles governing human and machine intelligence' (Allied Publishers 2009). Roger has just completed a one-year MSc in Advanced Computing at Imperial College, London, and is visiting India for 3 months prior to returning to his post in UK government research.