Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Amir Gargouri"'
Autor:
Amir Gargouri, Dorra Sellami Masmoudi
Publikováno v:
AEU - International Journal of Electronics and Communications. 67:513-520
This paper focuses on a new digital architecture of pulse mode neuro-fuzzy system (PMNFS) with on-chip learning ability. The main purpose goal is to make use of the outstanding features of neuro-fuzzy in function approximation, and implement a reconf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d30559777863555fceb80954f3d551c2
https://doi.org/10.1016/j.aeue.2012.11.011
https://doi.org/10.1016/j.aeue.2012.11.011
Autor:
Ben Mansour, Amir Gargouri, Boutheina Melliou, Eleni and Magiatis, Prokopios Bouaziz, Mohamed
BACKGROUND: Olive oil contains compounds with interesting biological activities which are influenced by the cultivar, the geographic origin and other factors. The aims of this work were to (1) investigate these factors in Neb Jmel olive oil from vari
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2127::3e6952b4df350201f7b7842f8dc82520
https://pergamos.lib.uoa.gr/uoa/dl/object/uoadl:3171457
https://pergamos.lib.uoa.gr/uoa/dl/object/uoadl:3171457
Publikováno v:
International Image Processing, Applications and Systems Conference.
This paper present a novel architecture for image segmentation. The design is based on the fuzzy c-means algorithm based gaussian function in pulse mode for reducing the large storage requirement. The proposed algorithm is tested in mammogram image s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::86b74504825827039ab5a18d00c18390
https://doi.org/10.1109/ipas.2014.7043286
https://doi.org/10.1109/ipas.2014.7043286
Autor:
Dorra Sellami Masmoudi, Amir Gargouri
Publikováno v:
2013 World Congress on Computer and Information Technology (WCCIT).
This paper presents a new compact hardware implementation of pulse mode Radial Basis Function Neural Network (RBFNN) with on-chip learning capacity. Since, hardware on-chip learning is a difficult issue, this work deals a hybrid process based into tw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9bd278c545b69240cf211adfb0d86591
https://doi.org/10.1109/wccit.2013.6618724
https://doi.org/10.1109/wccit.2013.6618724
Autor:
Dorra Sellami Masmoudi, Amir Gargouri
Publikováno v:
2013 International Conference on Control, Decision and Information Technologies (CoDIT).
This paper proposes a pulse mode neural network (PMNN) based image denoising operation. Known by their outstanding future, PMNN is gaining support in the field of hardware implementation thanks to its significant compactness and higher density of int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad991f99421a7a3fb082a3c960ff7c14
https://doi.org/10.1109/codit.2013.6689632
https://doi.org/10.1109/codit.2013.6689632
Autor:
Dorra Sellami Masmoudi, Amir Gargouri
Publikováno v:
Journal of Advanced Computer Science & Technology. 2
A hardware implementation of pulse mode Radial Basis Function Neural Network (RBFNN) with on-chip learning ability is proposed in this paper. Pulse mode presents an emerging technology in digital implementation of neural networks thanks to its higher
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::796c7b72636c4ef8ae84d9cd82624e55
https://doi.org/10.14419/jacst.v2i1.547
https://doi.org/10.14419/jacst.v2i1.547
Publikováno v:
DTIS
In this paper, we propose a new architecture of Pulse Mode Neural Network (PMNN) with very simple activation function. Pulse mode is gaining support in the field of hardware Neural Networks thanks to its higher density of integration. However, the co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4009d07e6cd8e748bbc2703b2c8fcde4
https://doi.org/10.1109/dtis.2012.6232959
https://doi.org/10.1109/dtis.2012.6232959
Publikováno v:
2010 7th International Multi- Conference on Systems, Signals and Devices.
In this paper, we have proposed a new architecture of RBFNN. Neural network efficiency in embedded systems offers the possibility of reconfiguration and the genericity of the solution. Indeed, the same integrated system can approximate any input-outp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::55ffddb0d9654356f329c4d37cef1ce4
https://doi.org/10.1109/ssd.2010.5585520
https://doi.org/10.1109/ssd.2010.5585520
Publikováno v:
International Journal of High Performance Systems Architecture. 4:132
A key task in the hardware implementation of neural networks is the design of activation functions. We focus in this paper on hardware driven simple implementation of a bell-shaped function BSF avoiding complexity and reducing hardware resources with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa35ea8cd50dc3c18e7cdf48fb50ebd9
https://doi.org/10.1504/ijhpsa.2013.055224
https://doi.org/10.1504/ijhpsa.2013.055224
Publikováno v:
International Journal of Innovative Computing and Applications. 3:188
In this paper, we propose a very compact implementation of a pulse mode radial basis activation function (RBF). The main idea is to make use of the powerful means of RBF neural networks in function approximation and implement a reconfigurable hardwar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd09be2254f9cd281ec77eb1372c67ed
https://doi.org/10.1504/ijica.2011.044567
https://doi.org/10.1504/ijica.2011.044567