Title :
Equivalence between RAM-based neural networks and probabilistic automata
Author :
De Souto, Marcilio C P ; Ludermir, Teresa B. ; De Oliveira, Wilson R.
Author_Institution :
Dept. of Informatics & Appl. Math., Fed. Univ. of Rio Grande do Norte, Natal, Brazil
fDate :
7/1/2005 12:00:00 AM
Abstract :
In this letter, the computational power of a class of random access memory (RAM)-based neural networks, called general single-layer sequential weightless neural networks (GSSWNNs), is analyzed. The theoretical results presented, besides helping the understanding of the temporal behavior of these networks, could also provide useful insights for the developing of new learning algorithms.
Keywords :
computability; learning automata; neural nets; probabilistic automata; random-access storage; learning algorithm; probabilistic automata; random access memory based neural network; single layer sequential weightless neural network; temporal behavior; Computer networks; Informatics; Learning automata; Mathematics; Neural networks; Neurons; Physics; Random access memory; Table lookup; Transfer functions; Automata theory; RAM-based neural networks; computability; probabilistic automata; weightless neural networks (WNNs); Algorithms; Computer Simulation; Models, Statistical; Neural Networks (Computer); Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2005.849838
