The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak
Multilayer perceptron network (MLP) has been recognized as a powerful tool for many applications including classification. Selection of the activation functions in the multilayer perceptron (MLP) network plays an essential role on the network performance. This paper presents comparison study of diff...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Universiti Teknologi MARA, Pulau Pinang & Pusat Penerbitan Universiti (UPENA)
2012
|
| Online Access: | https://ir.uitm.edu.my/id/eprint/8857/ |
| _version_ | 1848802901098496000 |
|---|---|
| author | Isa, Iza Sazanita Sulaiman, Siti Noraini Ahmad, Azizah Ad. Fauzi, Normasni Ishak, Nurul Huda |
| author_facet | Isa, Iza Sazanita Sulaiman, Siti Noraini Ahmad, Azizah Ad. Fauzi, Normasni Ishak, Nurul Huda |
| author_sort | Isa, Iza Sazanita |
| building | UiTM Institutional Repository |
| collection | Online Access |
| description | Multilayer perceptron network (MLP) has been recognized as a powerful tool for many applications including classification. Selection of the activation functions in the multilayer perceptron (MLP) network plays an essential role on the network performance. This paper presents comparison study of different MLP activation function; for three different classification cases which are breast cancer, thyroid disease and weather classification. The activation functions under investigation are sigmoid and hyperbolic tangent. In this study, the MLP network was trained and tested to investigate the ability of network to classify the breast cancer between benign and malignant cell, thyroid disease are classified into normal, hyper or hypo thyroid while the weather conditions are classified into four types; rain, cloudy, dry day and storm. Levenberg-Marquardt algorithm is used to train the MLP network since it is the fastest training and ensure the best converges towards a minimum error. |
| first_indexed | 2025-11-14T21:30:42Z |
| format | Article |
| id | uitm-8857 |
| institution | Universiti Teknologi MARA |
| institution_category | Local University |
| last_indexed | 2025-11-14T21:30:42Z |
| publishDate | 2012 |
| publisher | Universiti Teknologi MARA, Pulau Pinang & Pusat Penerbitan Universiti (UPENA) |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uitm-88572017-09-21T09:17:34Z https://ir.uitm.edu.my/id/eprint/8857/ The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak esteem Isa, Iza Sazanita Sulaiman, Siti Noraini Ahmad, Azizah Ad. Fauzi, Normasni Ishak, Nurul Huda Multilayer perceptron network (MLP) has been recognized as a powerful tool for many applications including classification. Selection of the activation functions in the multilayer perceptron (MLP) network plays an essential role on the network performance. This paper presents comparison study of different MLP activation function; for three different classification cases which are breast cancer, thyroid disease and weather classification. The activation functions under investigation are sigmoid and hyperbolic tangent. In this study, the MLP network was trained and tested to investigate the ability of network to classify the breast cancer between benign and malignant cell, thyroid disease are classified into normal, hyper or hypo thyroid while the weather conditions are classified into four types; rain, cloudy, dry day and storm. Levenberg-Marquardt algorithm is used to train the MLP network since it is the fastest training and ensure the best converges towards a minimum error. Universiti Teknologi MARA, Pulau Pinang & Pusat Penerbitan Universiti (UPENA) 2012 Article PeerReviewed Isa, Iza Sazanita and Sulaiman, Siti Noraini and Ahmad, Azizah and Ad. Fauzi, Normasni and Ishak, Nurul Huda (2012) The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak. (2012) Esteem Academic Journal <https://ir.uitm.edu.my/view/publication/Esteem_Academic_Journal.html>, 8 (1). pp. 64-74. ISSN 1675-7939 |
| spellingShingle | Isa, Iza Sazanita Sulaiman, Siti Noraini Ahmad, Azizah Ad. Fauzi, Normasni Ishak, Nurul Huda The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak |
| title | The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak |
| title_full | The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak |
| title_fullStr | The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak |
| title_full_unstemmed | The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak |
| title_short | The effect of activation functions in MLP performance based on different classification cases / Iza Sazanita Isa, Siti Noraini Sulaiman, Azizah Ahmad, Normasni Ad. Fauzi and Nurul Huda Ishak |
| title_sort | effect of activation functions in mlp performance based on different classification cases / iza sazanita isa, siti noraini sulaiman, azizah ahmad, normasni ad. fauzi and nurul huda ishak |
| url | https://ir.uitm.edu.my/id/eprint/8857/ |