%0 Report %D 2008 %T The Maryland Large-Scale Integrated Neurocognitive Architecture %A Reggia, James A. %A Tagamets,M. %A Contreras-Vidal,J. %A Jacobs, David W. %A Weems,S. %A Naqvi,W. %A Yang,C. %K *COMPUTATIONS %K *HYBRID SYSTEMS %K *NEURAL NETS %K *NEUROCOGNITIVE ARCHITECTURE %K ADAPTIVE SYSTEMS %K Artificial intelligence %K BRAIN %K Cognition %K COMPUTER PROGRAMMING %K COMPUTER PROGRAMMING AND SOFTWARE %K HYBRID AI %K Machine intelligence %K MECHANICAL ORGANS %K MODULAR CONSTRUCTION %K NERVOUS SYSTEM %K PE61101E %K PLASTIC PROPERTIES %K PROCESSING EQUIPMENT %K RECURRENT NEURAL NETWORK %X 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. %I University of Maryland College Park %8 2008/03// %G eng %U http://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA481261