Multi-Backpropagation network
Neural Network is a computational paradigm that comprises several disciplines such as mathematics, statistic, biology and philosophy.Neural Network has been implemented in many applications; in software and even hardware. In most cases, Neural Network considered large amount of data, as it will be...
| Príomhchruthaitheoirí: | , , |
|---|---|
| Formáid: | Conference or Workshop Item |
| Teanga: | English |
| Foilsithe / Cruthaithe: |
2002
|
| Ábhair: | |
| Rochtain ar líne: | https://repo.uum.edu.my/id/eprint/3420/1/WH4.pdf |
| _version_ | 1825740143488663552 |
|---|---|
| author | Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib |
| author_facet | Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib |
| author_sort | Wan Ishak, Wan Hussain |
| collection | UUM |
| description | Neural Network is a computational paradigm that comprises
several disciplines such as mathematics, statistic, biology
and philosophy.Neural Network has been implemented in many applications; in software and even hardware. In most cases, Neural Network considered large amount of data, as it will be teach to learn or memorize the data as the knowledge. The learning mechanism for Neural Network is its learning algorithm. Backpropagation (or backprop) algorithm is one of the well-known algorithms in neural networks. Backpropagation network with hidden layer able to process and model more complex problem. However, as some problem involve a large amount of data, the network would be more difficult to train. More input units or hidden units could increase the model size and increase its computational complexity. Synonym to human learning, a complex problem required some time to learn or memorize. Therefore, reducing the network complexity would be an advantage to the network. This paper proposed multi-backpropagation network to reduce the size of a large backpropagation network. The domain for the illustration presented in this paper is the Myocardial Infarction disease. This approach do not required any alteration of the algorithm. The large network is split into several smaller networks, which act as a specialized network. This approach could also reduce the redundant data and reduce the training epochs. |
| first_indexed | 2024-07-04T05:21:54Z |
| format | Conference or Workshop Item |
| id | uum-3420 |
| institution | Universiti Utara Malaysia |
| language | English |
| last_indexed | 2024-07-04T05:21:54Z |
| publishDate | 2002 |
| record_format | eprints |
| spelling | uum-34202011-08-15T02:17:18Z https://repo.uum.edu.my/id/eprint/3420/ Multi-Backpropagation network Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib QA76 Computer software Neural Network is a computational paradigm that comprises several disciplines such as mathematics, statistic, biology and philosophy.Neural Network has been implemented in many applications; in software and even hardware. In most cases, Neural Network considered large amount of data, as it will be teach to learn or memorize the data as the knowledge. The learning mechanism for Neural Network is its learning algorithm. Backpropagation (or backprop) algorithm is one of the well-known algorithms in neural networks. Backpropagation network with hidden layer able to process and model more complex problem. However, as some problem involve a large amount of data, the network would be more difficult to train. More input units or hidden units could increase the model size and increase its computational complexity. Synonym to human learning, a complex problem required some time to learn or memorize. Therefore, reducing the network complexity would be an advantage to the network. This paper proposed multi-backpropagation network to reduce the size of a large backpropagation network. The domain for the illustration presented in this paper is the Myocardial Infarction disease. This approach do not required any alteration of the algorithm. The large network is split into several smaller networks, which act as a specialized network. This approach could also reduce the redundant data and reduce the training epochs. 2002 Conference or Workshop Item NonPeerReviewed application/pdf en https://repo.uum.edu.my/id/eprint/3420/1/WH4.pdf Wan Ishak, Wan Hussain and Siraj, Fadzilah and Othman, Abu Talib (2002) Multi-Backpropagation network. In: Proceedings of the International Conference on Artificial Intelligence in Engineering and Technology , 17-18 June 2002, Kota Kinabalu, Sabah. (Unpublished) |
| spellingShingle | QA76 Computer software Wan Ishak, Wan Hussain Siraj, Fadzilah Othman, Abu Talib Multi-Backpropagation network |
| title | Multi-Backpropagation network |
| title_full | Multi-Backpropagation network |
| title_fullStr | Multi-Backpropagation network |
| title_full_unstemmed | Multi-Backpropagation network |
| title_short | Multi-Backpropagation network |
| title_sort | multi backpropagation network |
| topic | QA76 Computer software |
| url | https://repo.uum.edu.my/id/eprint/3420/1/WH4.pdf |
| work_keys_str_mv | AT wanishakwanhussain multibackpropagationnetwork AT sirajfadzilah multibackpropagationnetwork AT othmanabutalib multibackpropagationnetwork |