The Maryland Large-Scale Integrated Neurocognitive Architecture

TitleThe Maryland Large-Scale Integrated Neurocognitive Architecture
Publication TypeReports
Year of Publication2008
AuthorsReggia JA, Tagamets M, Contreras-Vidal J, Jacobs DW, Weems S, Naqvi W, Yang C
Date Published2008/03//
InstitutionUniversity of Maryland College Park
Keywords*COMPUTATIONS, *HYBRID SYSTEMS, *NEURAL NETS, *NEUROCOGNITIVE ARCHITECTURE, ADAPTIVE SYSTEMS, Artificial intelligence, BRAIN, Cognition, COMPUTER PROGRAMMING, COMPUTER PROGRAMMING AND SOFTWARE, HYBRID AI, Machine intelligence, MECHANICAL ORGANS, MODULAR CONSTRUCTION, NERVOUS SYSTEM, PE61101E, PLASTIC PROPERTIES, PROCESSING EQUIPMENT, RECURRENT NEURAL NETWORK
Abstract

Recent progress in neural computation, high performance computing, neuroscience and cognitive science suggests that an effort to produce a general-purpose, adaptive machine intelligence is likely to yield a qualitatively more powerful system than those currently existing. Here we outline our progress in developing a framework for creating such a large-scale machine intelligence, or neurocognitive architecture that is based on the modularity, dynamics and plasticity of the human brain. We successfully implemented three intermediate-scale parts of such a system, and these are described. Based on this experience, we concluded that for the short term, optimal results would be obtained by using a hybrid design including neural, symbolic AI, and artificial life methods. We propose a three-tiered architecture that integrates these different methods, and describe a prototype mini-Roboscout that we implemented and evaluated based on this architecture. We also examined, via computational experiments, the effectiveness of genetic programming as a design tool for recurrent neural networks, and the speed-up obtained for adaptive neural networks when they are executed on a graphical processing unit. We conclude that the implementation of a large-scale neurocognitive architecture is feasible, and outline a roadmap for proceeding.

URLhttp://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA481261