1986
DOI: 10.1063/1.36222
|View full text |Cite
|
Sign up to set email alerts
|

Influence of noise on the behaviour of an autoassociative neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

1988
1988
1993
1993

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 0 publications
0
3
0
Order By: Relevance
“…This provides yet another example of the possible beneficial aspects of noise in the processing of information by the central nervous system. The positive role of noise was recognized earlier by Buhmann andSchulten (1986, 1987), who found that noise, deliberately added to the deterministic equations governing individual neurons in a network, significantly enhanced the network's performance. They concluded that "...the noise...is an essential feature of the information processing capabilities of the neural network, and not a mere source of disturbance, better suppressed..."…”
Section: Discussionmentioning
confidence: 91%
“…This provides yet another example of the possible beneficial aspects of noise in the processing of information by the central nervous system. The positive role of noise was recognized earlier by Buhmann andSchulten (1986, 1987), who found that noise, deliberately added to the deterministic equations governing individual neurons in a network, significantly enhanced the network's performance. They concluded that "...the noise...is an essential feature of the information processing capabilities of the neural network, and not a mere source of disturbance, better suppressed..."…”
Section: Discussionmentioning
confidence: 91%
“…Therefore, A(t) can be thought to depend on relative membrane potentials of all neurons in the nerve system. The second term in the right-hand side of equation (1.2) represents the fluctuating contribution to the membrane potential due to the spontaneous fluctuation (Abeles (1982), Buhmann and Schulten (1986)). It is given by a stochastic differential of a Gaussian stochastic process w={w(t)lO<_t<~} called a Wiener process such that…”
Section: (12) Dx(t) = A(t)dt+ Dw(t)mentioning
confidence: 99%
“…means to take the mathematical expectation and the diffusion constant v is of the order of 10 (milli-volt)2/(milli-second) (Buhmann and Schulten (1986)). It is a standard result of the probability theory that the stochastic differential equation (1.2) determines a stochastic process x={x(t)lO<_t<~} called semi-martingale if the drift A(t) and the initial condition x(0) are given (Nelson (1967)).…”
Section: ) E[ldw(t)l 2] = Vdtmentioning
confidence: 99%