Title :
A reconfigurable continuous time recurrent neural network for evolvable hardware applications
Author :
Gallagher, John C. ; Boddhu, Sanjay K. ; Vigraham, Saranyan
Author_Institution :
Dept. of Comput. Sci. & Eng., Wright State Univ., Dayton, OH, USA
fDate :
29 June-1 July 2005
Abstract :
Evolvable hardware is reconfigurable hardware plus an evolutionary algorithm. Continuous time recurrent neural networks (CTRNNs) have been proposed for use as the reconfigurable hardware component. Until recently, however, nearly all CTRNN based EH was simulation based. This poster details a design for a reconfigurable analog CTRNN computer that supports both extrinsic and intrinsic CTRNN evolvable hardware.
Keywords :
analogue computers; continuous time systems; discrete time systems; evolutionary computation; reconfigurable architectures; recurrent neural nets; continuous time neural network; evolutionary algorithm; evolvable hardware; reconfigurable hardware; reconfigurable neural network; recurrent neural network; Analog computers; Application software; Computational modeling; Computer science; Control systems; Evolutionary computation; Neural network hardware; Neurons; Potentiometers; Recurrent neural networks;
Conference_Titel :
Evolvable Hardware, 2005. Proceedings. 2005 NASA/DoD Conference on
Print_ISBN :
0-7695-2399-4
