Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function
This paper discusses the artificial neural network (ANN) implementation into a field programmable gate array (FPGA). One of the most difficult problem encounters is the complex equation of the activation function namely sigmoid function. The sigmoid function is used as learning function to train the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UTeM
2017
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/21765/ http://umpir.ump.edu.my/id/eprint/21765/1/Sigmoid%20function%20implementation%20using%20the%20unequal%20segmentation.pdf |
| _version_ | 1848821427732480000 |
|---|---|
| author | Syahrulanuar, Ngah Rohani, Abu Bakar |
| author_facet | Syahrulanuar, Ngah Rohani, Abu Bakar |
| author_sort | Syahrulanuar, Ngah |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | This paper discusses the artificial neural network (ANN) implementation into a field programmable gate array (FPGA). One of the most difficult problem encounters is the complex equation of the activation function namely sigmoid function. The sigmoid function is used as learning function to train the neural network while its derivative is used as a network activation function for specifying the point at which the network should switch to a true state. In order to overcome this problem, two-steps approach which combined the unequal segmentation of the differential look-up table (USdLUT) and the second order nonlinear function (SONF) is proposed. Based on the analysis done, the deviation achieved using the proposed method is 95%. The result obtained is much better than the previous implementation that uses equal segmentation of differential look-up table. |
| first_indexed | 2025-11-15T02:25:11Z |
| format | Article |
| id | ump-21765 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T02:25:11Z |
| publishDate | 2017 |
| publisher | UTeM |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-217652018-09-19T07:10:38Z http://umpir.ump.edu.my/id/eprint/21765/ Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function Syahrulanuar, Ngah Rohani, Abu Bakar QA76 Computer software This paper discusses the artificial neural network (ANN) implementation into a field programmable gate array (FPGA). One of the most difficult problem encounters is the complex equation of the activation function namely sigmoid function. The sigmoid function is used as learning function to train the neural network while its derivative is used as a network activation function for specifying the point at which the network should switch to a true state. In order to overcome this problem, two-steps approach which combined the unequal segmentation of the differential look-up table (USdLUT) and the second order nonlinear function (SONF) is proposed. Based on the analysis done, the deviation achieved using the proposed method is 95%. The result obtained is much better than the previous implementation that uses equal segmentation of differential look-up table. UTeM 2017 Article PeerReviewed pdf en cc_by http://umpir.ump.edu.my/id/eprint/21765/1/Sigmoid%20function%20implementation%20using%20the%20unequal%20segmentation.pdf Syahrulanuar, Ngah and Rohani, Abu Bakar (2017) Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function. Journal of Telecommunication, Electronic and Computer Engineering, 9 (2-8). pp. 103-108. ISSN 2180-1843 (Print); 2289-8131 (Online). (Published) http://journal.utem.edu.my/index.php/jtec/article/view/2637/1704 |
| spellingShingle | QA76 Computer software Syahrulanuar, Ngah Rohani, Abu Bakar Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| title | Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| title_full | Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| title_fullStr | Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| title_full_unstemmed | Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| title_short | Sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| title_sort | sigmoid function implementation using the unequal segmentation of differential lookup table and second order nonlinear function |
| topic | QA76 Computer software |
| url | http://umpir.ump.edu.my/id/eprint/21765/ http://umpir.ump.edu.my/id/eprint/21765/ http://umpir.ump.edu.my/id/eprint/21765/1/Sigmoid%20function%20implementation%20using%20the%20unequal%20segmentation.pdf |