Title :
Doubly stochastic Poisson processes in artificial neural learning
Author_Institution :
Dept. of Electr. & Comput. Eng., Manitoba Univ., Winnipeg, Man., Canada
fDate :
1/1/1998 12:00:00 AM
Abstract :
This paper investigates neuron activation statistics in artificial neural networks employing stochastic arithmetic. It is shown that a doubly stochastic Poisson process is an appropriate model for the signals in these circuits
Keywords :
digital arithmetic; learning (artificial intelligence); neural nets; statistical analysis; stochastic processes; activation statistics; neural learning; neural networks; stochastic Poisson processes; stochastic arithmetic; Arithmetic; Artificial neural networks; Circuits; Computer networks; Fluctuations; Intelligent networks; Neurons; Signal processing; Statistics; Stochastic processes;
Journal_Title :
Neural Networks, IEEE Transactions on
