DocumentCode
2734444
Title
Funk2: A Distributed Processing Language for Reflective Tracing of a Large Critic-Selector Cognitive Architecture
Author
Morgan, Bo
Author_Institution
MIT Media Lab., Cambridge, MA, USA
fYear
2010
fDate
27-28 Sept. 2010
Firstpage
269
Lastpage
274
Abstract
We see the field of metareasoning to be the answer to many large organizational problems encountered when putting together an understandable cognitive architecture, capable of commonsense reasoning. In this paper we review the EM1 implementation of the Emotion Machine critic-selector architecture, as well as explain the current progress we have made in redesigning this first version implementation. For this purpose of redesign and large-scale implementation, we have written a novel programming language, Funk2, that focuses on efficient metareasoning and procedural reflection, the keystones of the critic-selector architecture. We present an argument for why the Funk2 programming language lends itself to easing the burden on programmers that prefer to not be restricted to strictly declarative programming paradigms by allowing the learning of critic and selector activation strengths by credit assignment through arbitrary procedural code.
Keywords
cognitive systems; common-sense reasoning; distributed processing; programming languages; EM1 implementation; Funk2 programming language; credit assignment; distributed processing language; emotion machine critic-selector cognitive architecture; metareasoning; procedural code; procedural reflection; programming language; selector activation; Architecture; Cognition; Computer architecture; Computer languages; Debugging; Instruction sets; Programming; EM1; Funk2; cognitive architecture; common sense reasoning; credit assignment; critic-selector architecture; metareasoning; programming language; reflective causal tracing;
fLanguage
English
Publisher
ieee
Conference_Titel
Self-Adaptive and Self-Organizing Systems Workshop (SASOW), 2010 Fourth IEEE International Conference on
Conference_Location
Budapest
Print_ISBN
978-1-4244-8684-7
Electronic_ISBN
978-0-7695-4229-4
Type
conf
DOI
10.1109/SASOW.2010.56
Filename
5729634
Link To Document