Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Désiré Bollé"'
Publikováno v:
Physica A: Statistical Mechanics and its Applications. 368:311-325
The three-state Ising neural network with synchronous updating and variable dilution is discussed starting from the appropriate Hamiltonians. The thermodynamic and retrieval properties are examined using replica mean-field theory. Capacity-temperatur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7c77ee00dadc9427b1eb48e079eb50f
https://doi.org/10.1016/j.physa.2005.12.052
https://doi.org/10.1016/j.physa.2005.12.052
Autor:
J. Busquets Blanco, Désiré Bollé
Publikováno v:
The European Physical Journal B. 47:281-290
The thermodynamic and retrieval properties of the Blume-Emery-Griffiths neural network with synchronous updating and variable dilution are studied using replica mean-field theory. Several forms of dilution are allowed by pruning the different types o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17191aa297fb2f0303b8376050031d77
https://doi.org/10.1140/epjb/e2005-00328-7
https://doi.org/10.1140/epjb/e2005-00328-7
Autor:
J. Busquets Blanco, Désiré Bollé
Publikováno v:
The European Physical Journal B. 42:397-406
Hamiltonians for general multi-state spin-glass systems with Ising symmetry are derived for both sequential and synchronous updating of the spins. The possibly different behaviour caused by the way of updating is studied in detail for the (anti)-ferr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24418920db2e96052f582c479bbfadea
https://doi.org/10.1140/epjb/e2004-00396-1
https://doi.org/10.1140/epjb/e2004-00396-1
Publikováno v:
Physica A: Statistical Mechanics and its Applications. 333:516-528
The time evolution of an exactly solvable layered feedforward neural network with three-state neurons and optimizing the mutual information is studied for arbitrary synaptic noise (temperature). Detailed stationary temperature-capacity and capacity-a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb08de833626c16793ab5095c7c91b62
https://doi.org/10.1016/j.physa.2003.10.033
https://doi.org/10.1016/j.physa.2003.10.033
Publikováno v:
Journal of Physics. A, Mathematical and General, 36, 10269-10277. IOP Publishing Ltd.
We introduce a spherical Hopfield-type neural network involving neurons and patterns that are continuous variables. We study both the thermodynamics and dynamics of this model. In order to have a retrieval phase a quartic term is added to the Hamilto
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::781f323c924dd6c95c08b33a4105cafa
https://hdl.handle.net/11245/1.215745
https://hdl.handle.net/11245/1.215745
Autor:
Désiré Bollé, P. Kozłowski
Publikováno v:
Journal of Physics A: Mathematical and General. 35:2093-2109
We study supervised learning and generalisation in coupled perceptrons trained on-line using two learning scenarios. In the first scenario the teacher and the student are independent networks and both are represented by an Ashkin-Teller perceptron. I
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3fb8faa77409d43f4b11e40d3f6b943e
https://doi.org/10.1088/0305-4470/35/9/302
https://doi.org/10.1088/0305-4470/35/9/302
Publikováno v:
Hong Kong University of Science and Technology
A model of noise reduction for signal processing and other optimization tasks is introduced. Each noise source puts a symmetric constraint on the space of the signal vector within a tolerance bound. When the number of noise sources increases, sequenc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6565f224c66ffa7a523953b0cde6c9b
https://doi.org/10.1088/0305-4470/33/7/101
https://doi.org/10.1088/0305-4470/33/7/101
Autor:
Drc Dominguez, Désiré Bollé
Publikováno v:
Scopus-Elsevier
A complete self-control mechanism is proposed in the dynamics of neural networks through the introduction of a time-dependent threshold, determined in function of both the noise and the pattern activity in the network. Especially for sparsely coded m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15ce50c7343f86ffb4b8cbb8aa419cde
https://doi.org/10.1103/physrevlett.80.2961
https://doi.org/10.1103/physrevlett.80.2961
Publikováno v:
Journal of Statistical Physics. 91:125-153
Using a probabilistic approach, the parallel dynamics of fully connected Q-Ising neural networks is studied for arbitrary Q. A novel recursive scheme is set up to determine the time evolution of the order parameters through the evolution of the distr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::94b85273ffe071ccb78d1aff9d78c183
https://doi.org/10.1023/a:1023088004195
https://doi.org/10.1023/a:1023088004195
Publikováno v:
Journal of Physics A: Mathematical and General. 30:2637-2652
We consider the behaviour of multi-state neural networks averaged over an extended monitoring period of their dynamics. Pattern reconstruction by clipping the activities is proposed, leading to an improvement in retrieval precision.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3283135f0c7e9d9bfb66dbb8cc55b1d
https://doi.org/10.1088/0305-4470/30/8/012
https://doi.org/10.1088/0305-4470/30/8/012