Development of a Large-Scale Integrated Neurocognitive Architecture - Part 2: Design and Architecture
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @TechReport{oai:drum.umd.edu:1903/3957,
-
title = "Development of a Large-Scale Integrated Neurocognitive
Architecture - Part 2: Design and Architecture",
-
author = "J. Reggia and M. Tagamets and J. Contreras-Vidal and
D. Jacobs and S. Weems and W. Naqvi and R. Winder and
T. Chabuk and J. Jung and C. Yang",
-
year = "2006",
-
institution = "University of Maryland",
-
number = "TR-CS-4827, UMIACS-TR-2006-43",
-
address = "USA",
-
month = oct,
-
keywords = "genetic algorithms, genetic programming, GPU",
-
URL = "https://drum.umd.edu/dspace/bitstream/1903/3957/1/MarylandPart2.pdf",
-
URL = "http://hdl.handle.net/1903/3957",
-
abstract = "In Part 1 of this report, we outlined a framework for
creating an intelligent agent based upon modelling the
large-scale functionality of the human brain. Building
on those results, we begin Part 2 by specifying the
behavioural requirements of a large-scale
neurocognitive architecture. The core of our long-term
approach remains focused on creating a network of
neuromorphic regions that provide the mechanisms needed
to meet these requirements. However, for the short term
of the next few years, it is likely that optimal
results will be obtained by using a hybrid design that
also includes symbolic methods from AI/cognitive
science and control processes from the field of
artificial life. We accordingly propose a three-tiered
architecture that integrates these different methods,
and describe an ongoing computational study of a
prototype 'mini-Roboscout' based on this architecture.
We also examine the implications of some non-standard
computational methods for developing a neurocognitive
agent. This examination included computational
experiments assessing the effectiveness of genetic
programming as a design tool for recurrent neural
networks for sequence processing, and experiments
measuring the speed-up obtained for adaptive neural
networks when they are executed on a graphical
processing unit (GPU) rather than a conventional CPU.
We conclude that the implementation of a large-scale
neurocognitive architecture is feasible, and outline a
roadmap for achieving this goal.",
-
bibsource = "OAI-PMH server at drum.umd.edu",
-
format = "1426146 bytes",
-
language = "en_US",
-
oai = "oai:drum.umd.edu:1903/3957",
-
relation = "UM Computer Science Department; CS-TR-4827; UMIACS;
UMIACS-TR-2006-43",
-
size = "32 pages",
- }
Genetic Programming entries for
James A Reggia
M Tagamets
Jose Luis Contreras-Vidal
David W Jacobs
Scott Weems
Waseem Naqvi
Ransom Winder
Timur Chabuk
Jin Hyuk Jung
Changjiang Yang
Citations