Zobrazeno 1 - 10
of 22
pro vyhledávání: '"M. Z. Rehman"'
Publikováno v:
Journal of ICT Research and Applications, Vol 7, Iss 2, Pp 103-116 (2014)
Training an artificial neural network is an optimization task, since it is desired to find optimal weight sets for a neural network during training process. Traditional training algorithms such as back propagation have some drawbacks such as getting
Externí odkaz:
https://doaj.org/article/29891c5a23f44754b2a12bd650c9eb36
Autor:
Muhammad Sadiq Hasan Zada, Nazri Mohd Nawi, M. Z. Rehman, Fazli Wahid, Muhammad Aamir, Muhammad Zulqarnain
Publikováno v:
Arabian Journal for Science and Engineering. 46:9237-9251
Contractive auto-encoder (CAE) is a type of auto-encoders and a deep learning algorithm that is based on multilayer training approach. It is considered as one of the most powerful, efficient and robust classification techniques, more specifically fea
Publikováno v:
Proceedings of the International Conference on Data Engineering 2015 (DaEng-2015) ISBN: 9789811317972
DaEng
DaEng
Meta-heuristic algorithms provide derivative-free solutions to optimize complex problems. Back-propagation Neural Network (BP) algorithm is one of the most commonly used and a popular technique to optimize the feed forward neural network training. Tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36d63efe50fc7515594f8fc106adf333
https://doi.org/10.1007/978-981-13-1799-6_34
https://doi.org/10.1007/978-981-13-1799-6_34
Publikováno v:
Rehman, M Z, Hallstrom, J & Havunen, J 2019, Current Step Generation and Measurement with Nanosecond Rise Time using Coaxial Cable Generator . in 2018 IEEE International Conference on High Voltage Engineering and Application : ICHVE 2018 ., 8642188, IEEE Institute of Electrical and Electronic Engineers, International Conference on High Voltage Engineering and Application, IEEE International Conference on High Voltage Engineering and Application, ICHVE 2018, Athens, Greece, 10/09/18 . https://doi.org/10.1109/ICHVE.2018.8642188
Current step generator is designed and tested based on charged coaxial cable for characterization of impulse current shunts. Current coil sensors were used with the shunts in measurement circuits for calibration of shunts. Solution is presented for c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00252cf7389b54e1e55a0a2ffccc7340
http://juuli.fi/Record/0338049919
http://juuli.fi/Record/0338049919
Publikováno v:
Journal of Computational and Theoretical Nanoscience. 13:706-714
An improved Bat algorithm with Gaussian distribution random walk (BAGD) is introduced in this paper. The original Bat algorithm has a problem of random large step length that leads to sub-optimal solutions in the search space and it cannot solve high
Autor:
Adamu Abubakar, Abdullah Khan, Nazri Mohd Nawi, Teh Ying Wah, M. Z. Rehman, Haruna Chiroma, Tutut Herawan
Publikováno v:
Journal of Computational and Theoretical Nanoscience. 13:450-460
Accelerated Particle Swarm Optimization (APSO) algorithm is one of the latest additions to the group of meta-heuristic nature inspired algorithms which provides derivative-free solutions to solve complex problems. Meanwhile, the Levenberg Marquardt B
Autor:
Rashid Naseem, Nazri Mohd Nawi, Jamal Uddin, Norhamreeza Abdul Hamid, M. Z. Rehman, Abdullah Khan
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319512792
SCDM
SCDM
This paper presents a Metahybrid algorithm that consists of the dual combination of Wolf Search (WS) and Elman Recurrent Neural Network (ERNN). ERNN is one of the most efficient feed forward neural network learning algorithm. Since ERNN uses gradient
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c66dbc3541ead7c4101ed566e7a469c9
https://doi.org/10.1007/978-3-319-51281-5_2
https://doi.org/10.1007/978-3-319-51281-5_2
Autor:
M. Z. Rehman, Norhamreeza AbdulHamid, Atta Ullah, Haruna Chiroma, Rahmat Shah, Nazri Mohd Nawi, Abdullah Khan, Nasreen Akhter
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319512792
SCDM
SCDM
An innovative metaheuristic based algorithm Chicken Swarm Optimization (CSO) is inspired by characteristics of chicken flock. CSO is particularly suitable for the investigation in candidate solutions for large spaces. This paper hybridize the CSO alg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a05df1bf5ef41c5436e919d05fcced4b
https://doi.org/10.1007/978-3-319-51281-5_13
https://doi.org/10.1007/978-3-319-51281-5_13
Publikováno v:
Journal of ICT Research and Applications, Vol 7, Iss 2, Pp 103-116 (2014)
Training an artificial neural network is an optimization task, since it is desired to find optimal weight sets for a neural network during training process. Traditional training algorithms such as back propagation have some drawbacks such as getting
Publikováno v:
Procedia Technology. 11:32-39
Recently, the popularity of artificial neural networks (ANN) is increasing since its capacity to model very complex problems in the area of Machine Learning, Data Mining and Pattern Recognition. Improving training efficacy of ANN based algorithm is a