Title :
TInMANN: the integer Markovian artificial neural network
Author :
Van den Bout, David E. ; Miller, Thomas K., III
Author_Institution :
Dept. of Electr. & Comput. Eng., North Carolina State Univ., Raleigh, NC, USA
Abstract :
A massively parallel, all-digital, stochastic digital architecture called TInMANN is described. It performs competitive and Kohonen types of learning at rates as high as 145000 training examples per second regardless of network size. Simulations of TInMANN, both with and without its conscience mechanism activated, demonstrate its effectiveness on a number of example problems.<>
Keywords :
Markov processes; learning systems; neural nets; parallel architectures; Kohonen learning; TInMANN; competitive learning; conscience mechanism; integer Markovian artificial neural network; massively parallel architecture; stochastic digital architecture; Learning systems; Markov processes; Neural networks; Parallel architectures;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118700
