文档介绍：Fourier works
Adrian Silvescu
Artificial Intelligence Research Group
Department puter Science
Iowa State University, Ames, IA 50010
Email:******@
Abstract
A new kind of neuron model that has a Fourier-like IN/OUT function
is introduced. The model is discussed in a general theoretical framework
and pleteness theorems are presented. Current experimental
results show that the new model outperforms by a large margin both in
representational power and convergence speed the classical mathematical
model of neuron based on weighted sum of inputs filtered by a nonlinear
function. The new model is also appealing from a neurophysiological point
of view because it produces a more realistic representation by considering
the inputs as oscillations.
1 Introduction
The first mathematical model of a neuron was proposed by McCulloch & Pitts[1943].
The underlying idea that this model tries to capture is that the response func-
tion of a neuron is a weighted sum of its inputs filtered through a nonlinear
function: y = h( wixi + θ).
Much progress has been done in the field of works since that time
but this idea stillP remained a very fundamental one. Although the model of the
computational unit(neuron) per se is simple, works are -
puters, higher levels plexity being achieved by connecting many neurons
together.
In this paper we try to propose m