Title :
The Correspondence Between Deterministic and Stochastic Digital Neurons: Analysis and Methodology
Author :
Geretti, Luca ; Abramo, Antonio
Author_Institution :
Dipt. di Ing. Elettr., Gestionale e Meccanica (DIEGM), Univ. of Udine, Udine
Abstract :
This paper analyzes the criteria for the direct correspondence between a deterministic neural network and its stochastic counterpart, and presents the guidelines that have been derived to establish such a correspondence during the design of a neural network application. In particular, the role of the slope and bias of the neuron activation function and that of the noise of its output have been addressed, thus filling a specific literature gap. This paper presents the results that have been theoretically derived in this regard, together with the simulations of few relevant application examples that have been performed to support them.
Keywords :
neural nets; stochastic processes; deterministic neural network; deterministic neurons; direct correspondence; neuron activation function; stochastic digital neurons; stochastic neural network; Deterministic equivalence; FPGA implementation; stochastic neuron; Algorithms; Computer Simulation; Feedback; Models, Statistical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted; Signal Processing, Computer-Assisted; Stochastic Processes;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2008.2001775