In this paper, dependence of storage capacity of an analogue associative memory model using nonmonotonic neurons on static synaptic noise and static threshold noise is shown. This dependence is analytically calculated by means of the self-consistent signal-to-noise analysis (SCSNA) proposed by Shiino and Fukai. It is known that the storage capacity of an associative memory model can be improved markedly by replacing the usual sigmoid neurons with nonmonotonic ones, and the Hopfield model has theoretically been shown to be fairly robust against introducing the static synaptic noise. In this paper, it is shown that when the monotonicity of neuron is high, the storage capacity decreases rapidly according to an increase of the static synaptic noise. It is also shown that the reduction of the storage capacity is more sensitive to an increase in the static threshold noise than to the increase in the static synaptic noise.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kazushi MIMURA, Masato OKADA, Koji KURATA, "Robustness to Noise of Associative Memory Using Nonmonotonic Analogue Neurons" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 8, pp. 928-932, August 1998, doi: .
Abstract: In this paper, dependence of storage capacity of an analogue associative memory model using nonmonotonic neurons on static synaptic noise and static threshold noise is shown. This dependence is analytically calculated by means of the self-consistent signal-to-noise analysis (SCSNA) proposed by Shiino and Fukai. It is known that the storage capacity of an associative memory model can be improved markedly by replacing the usual sigmoid neurons with nonmonotonic ones, and the Hopfield model has theoretically been shown to be fairly robust against introducing the static synaptic noise. In this paper, it is shown that when the monotonicity of neuron is high, the storage capacity decreases rapidly according to an increase of the static synaptic noise. It is also shown that the reduction of the storage capacity is more sensitive to an increase in the static threshold noise than to the increase in the static synaptic noise.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_8_928/_p
Copy
@ARTICLE{e81-d_8_928,
author={Kazushi MIMURA, Masato OKADA, Koji KURATA, },
journal={IEICE TRANSACTIONS on Information},
title={Robustness to Noise of Associative Memory Using Nonmonotonic Analogue Neurons},
year={1998},
volume={E81-D},
number={8},
pages={928-932},
abstract={In this paper, dependence of storage capacity of an analogue associative memory model using nonmonotonic neurons on static synaptic noise and static threshold noise is shown. This dependence is analytically calculated by means of the self-consistent signal-to-noise analysis (SCSNA) proposed by Shiino and Fukai. It is known that the storage capacity of an associative memory model can be improved markedly by replacing the usual sigmoid neurons with nonmonotonic ones, and the Hopfield model has theoretically been shown to be fairly robust against introducing the static synaptic noise. In this paper, it is shown that when the monotonicity of neuron is high, the storage capacity decreases rapidly according to an increase of the static synaptic noise. It is also shown that the reduction of the storage capacity is more sensitive to an increase in the static threshold noise than to the increase in the static synaptic noise.},
keywords={},
doi={},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Robustness to Noise of Associative Memory Using Nonmonotonic Analogue Neurons
T2 - IEICE TRANSACTIONS on Information
SP - 928
EP - 932
AU - Kazushi MIMURA
AU - Masato OKADA
AU - Koji KURATA
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 1998
AB - In this paper, dependence of storage capacity of an analogue associative memory model using nonmonotonic neurons on static synaptic noise and static threshold noise is shown. This dependence is analytically calculated by means of the self-consistent signal-to-noise analysis (SCSNA) proposed by Shiino and Fukai. It is known that the storage capacity of an associative memory model can be improved markedly by replacing the usual sigmoid neurons with nonmonotonic ones, and the Hopfield model has theoretically been shown to be fairly robust against introducing the static synaptic noise. In this paper, it is shown that when the monotonicity of neuron is high, the storage capacity decreases rapidly according to an increase of the static synaptic noise. It is also shown that the reduction of the storage capacity is more sensitive to an increase in the static threshold noise than to the increase in the static synaptic noise.
ER -