Particle Swarm Optimization (PSO) for Training Optimization on Convolutional Neural Network (CNN)

Dikirim tanggal 09-09-2016 oleh Admin IOER

Deskripsi Singkat

Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of research- es had been undertaken on the improvement of the standard neural network. One of the most pro- mising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO) in Convolutional Neural Networks (CNNs), which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recog- nition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN. The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.

  • Ilmu Komputer

Whoops, looks like something went wrong.

1/1 ErrorException in Filesystem.php line 111: file_put_contents(): Only 0 of 267 bytes written, possibly out of free disk space

  1. in Filesystem.php line 111
  2. at HandleExceptions->handleError('2', 'file_put_contents(): Only 0 of 267 bytes written, possibly out of free disk space', '/home/sipw3565/public_html/', '111', array('path' => '/home/sipw3565/public_html/', 'contents' => 'a:4:{s:6:"_token";s:40:"I6CCDvX2xLEdMoxG3Gv3PusM13iiA1gMmAUF3wcV";s:9:"_previous";a:1:{s:3:"url";s:30:"";}s:9:"_sf2_meta";a:3:{s:1:"u";i:1603540604;s:1:"c";i:1603540604;s:1:"l";s:1:"0";}s:5:"flash";a:2:{s:3:"old";a:0:{}s:3:"new";a:0:{}}}', 'lock' => true))
  3. at file_put_contents('/home/sipw3565/public_html/', 'a:4:{s:6:"_token";s:40:"I6CCDvX2xLEdMoxG3Gv3PusM13iiA1gMmAUF3wcV";s:9:"_previous";a:1:{s:3:"url";s:30:"";}s:9:"_sf2_meta";a:3:{s:1:"u";i:1603540604;s:1:"c";i:1603540604;s:1:"l";s:1:"0";}s:5:"flash";a:2:{s:3:"old";a:0:{}s:3:"new";a:0:{}}}', '2') in Filesystem.php line 111
  4. at Filesystem->put('/home/sipw3565/public_html/', 'a:4:{s:6:"_token";s:40:"I6CCDvX2xLEdMoxG3Gv3PusM13iiA1gMmAUF3wcV";s:9:"_previous";a:1:{s:3:"url";s:30:"";}s:9:"_sf2_meta";a:3:{s:1:"u";i:1603540604;s:1:"c";i:1603540604;s:1:"l";s:1:"0";}s:5:"flash";a:2:{s:3:"old";a:0:{}s:3:"new";a:0:{}}}', true) in FileSessionHandler.php line 83
  5. at FileSessionHandler->write('74a91a57952ff17002f42d6216c6f1754a8021b8', 'a:4:{s:6:"_token";s:40:"I6CCDvX2xLEdMoxG3Gv3PusM13iiA1gMmAUF3wcV";s:9:"_previous";a:1:{s:3:"url";s:30:"";}s:9:"_sf2_meta";a:3:{s:1:"u";i:1603540604;s:1:"c";i:1603540604;s:1:"l";s:1:"0";}s:5:"flash";a:2:{s:3:"old";a:0:{}s:3:"new";a:0:{}}}') in Store.php line 262
  6. at Store->save() in StartSession.php line 88
  7. at StartSession->terminate(object(Request), object(Response)) in Kernel.php line 155
  8. at Kernel->terminate(object(Request), object(Response)) in index.php line 58