OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES
In this paper, Optimal Brain Surgeon (OBS) pruning algorithm is proposed to optimize network architecture with respect to testing patterns error and overcoming the overlitting problem. Turning process is used as case study to improve the performance of the neural network-surface roughness model. Us...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Baghdad
2005-09-01
|
| Series: | Journal of Engineering |
| Online Access: | https://www.joe.uobaghdad.edu.iq/index.php/main/article/view/3347 |
| _version_ | 1827321643564793856 |
|---|---|
| author | Bahaa Ibraheem Kazem Ali Khudhair Mutlag |
| author_facet | Bahaa Ibraheem Kazem Ali Khudhair Mutlag |
| author_sort | Bahaa Ibraheem Kazem |
| collection | DOAJ |
| description |
In this paper, Optimal Brain Surgeon (OBS) pruning algorithm is proposed to optimize network architecture with respect to testing patterns error and overcoming the overlitting problem. Turning process is used as case study to improve the performance of the neural network-surface roughness model. Using the proposed algorithm reduced the prediction error on testing patterns from 0.6237 to 0.2854 based on the absolute percent error estimate. Also, a noticeable improvement is made in correlation coefficient from 0.8656 to 0.9807 making the network more reliable for new operating conditions.
|
| first_indexed | 2024-03-07T15:37:02Z |
| format | Article |
| id | doaj.art-beab772ecd594dfc9594e975dc496daa |
| institution | Directory Open Access Journal |
| issn | 1726-4073 2520-3339 |
| language | English |
| last_indexed | 2024-04-25T01:10:45Z |
| publishDate | 2005-09-01 |
| publisher | University of Baghdad |
| record_format | Article |
| series | Journal of Engineering |
| spelling | doaj.art-beab772ecd594dfc9594e975dc496daa2024-03-10T09:52:35ZengUniversity of BaghdadJournal of Engineering1726-40732520-33392005-09-01110310.31026/j.eng.2005.03.05OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSESBahaa Ibraheem KazemAli Khudhair Mutlag In this paper, Optimal Brain Surgeon (OBS) pruning algorithm is proposed to optimize network architecture with respect to testing patterns error and overcoming the overlitting problem. Turning process is used as case study to improve the performance of the neural network-surface roughness model. Using the proposed algorithm reduced the prediction error on testing patterns from 0.6237 to 0.2854 based on the absolute percent error estimate. Also, a noticeable improvement is made in correlation coefficient from 0.8656 to 0.9807 making the network more reliable for new operating conditions. https://www.joe.uobaghdad.edu.iq/index.php/main/article/view/3347 |
| spellingShingle | Bahaa Ibraheem Kazem Ali Khudhair Mutlag OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES Journal of Engineering |
| title | OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES |
| title_full | OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES |
| title_fullStr | OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES |
| title_full_unstemmed | OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES |
| title_short | OPTIMAL BRAIN SURGEON PRUNING OF NEURAL NETWORK MODELS OF MANUFACTURING PROCESSES |
| title_sort | optimal brain surgeon pruning of neural network models of manufacturing processes |
| url | https://www.joe.uobaghdad.edu.iq/index.php/main/article/view/3347 |
| work_keys_str_mv | AT bahaaibraheemkazem optimalbrainsurgeonpruningofneuralnetworkmodelsofmanufacturingprocesses AT alikhudhairmutlag optimalbrainsurgeonpruningofneuralnetworkmodelsofmanufacturingprocesses |