Biologically Inspired Cognitive Architectures |
Written by Ricardo Sanz | |||
Tuesday, 09 September 2008 | |||
The ASLab team presents two contributions there:
More information can be found in the BICA Symposium Website. This fundamental scientific problem calls for the design and experimental study of biologically inspired cognitive architectures (BICA). Despite a substantial number of recent conferences and workshops focused on computational theories of biological information processing, this topic of research remains underrepresented. Some of its valuable outcomes are just beginning to emerge in publications. It is therefore our view that a forum, under the auspices of the AAAI 2008 Fall Symposia, dedicated to the topic of BICA is both timely and beneficial in stimulating further research in this field. The primary objective of this symposium is to showcase recent modeling and rapid prototyping experience aimed at building architectures of cognitive agents that have been inspired by the human brain and, in a definite sense, operate like the human mind. At the same time, theoretical discussion of the underlying mechanisms will be equally encouraged. Biological constraints on human cognition informed by neuroscience and psychology become most valuable, when it comes to a computational description of higher cognition. Some of them are pre-programmed to develop and are critical for robustness and adaptability in real-world situations. On the other hand, the main body of human cognitive abilities is acquired through learning and meta-learning (cognitive growth), which thus are the key to development of adult human-level intelligence. Learning can be achieved not only via trial and error, but most importantly, through social and teaching paradigms: by instruction, by example, and by guided exploration (example: “learning by reading"). From this point of view, it is important (A) to determine a “critical mass” of capabilities that together enable bootstrapped learning, (B) to find the right architecture for their implementation, and (C) to be able to measure the outcome. Topics of the program include the following:
|
|||
Last Updated ( Saturday, 13 December 2008 ) |