Title :
A neurophysiologically inspired hippocampus based associative-ART Artificial neural network architecture
Author :
Vineyard, Craig M. ; Verzi, Stephen J. ; Bernard, Michael L. ; Taylor, Shawn E. ; Shaneyfelt, Wendy L. ; Dubicka, Irene ; McClain, Jonathan T. ; Caudell, Thomas P.
Author_Institution :
Sandia Nat. Labs., Albuquerque, NM, USA
fDate :
July 31 2011-Aug. 5 2011
Abstract :
Hippocampus within medial temporal lobe of the brain is essentially involved in episodic memory formation. Rather than simply being a mechanism of storing information, episodic memory associates information such as the spatial and temporal context of an event. Using hippocampus neurophysiology and functionality as an inspiration, we have developed an artificial neural network architecture called Associative-ART to associate k-tuples of inputs. In this paper we present an overview of hippocampus neurophysiology, explain the design of our neural network architecture, and present experimental results from an implementation of our architecture.
Keywords :
neural nets; neurophysiology; associative-ART artificial neural network architecture; episodic memory formation; hippocampus functionality; hippocampus neurophysiology; neurophysiologically inspired hippocampus; Artificial neural networks; Computer architecture; Encoding; Hippocampus; Laboratories; Neurophysiology; Subspace constraints;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033487