Research Commons
      • Browse 
        • Communities & Collections
        • Titles
        • Authors
        • By Issue Date
        • Subjects
        • Types
        • Series
      • Help 
        • About
        • Collection Policy
        • OA Mandate Guidelines
        • Guidelines FAQ
        • Contact Us
      • My Account 
        • Sign In
        • Register
      View Item 
      •   Research Commons
      • University of Waikato Research
      • Computing and Mathematical Sciences
      • Computing and Mathematical Sciences Papers
      • View Item
      •   Research Commons
      • University of Waikato Research
      • Computing and Mathematical Sciences
      • Computing and Mathematical Sciences Papers
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Using swarm optimization to enhance autoencoder’s images

      Doaud, Maisa; Mayo, Michael
      Thumbnail
      Files
      USB Proc-paper-Doaud-Mayo.pdf
      Published version, 1.040Mb
      Find in your library  
      Citation
      Export citation
      Doaud, M., & Mayo, M. (2017). Using swarm optimization to enhance autoencoder’s images. In V. Torra, Y. Narukawa, A. Honda, & S. Inoue (Eds.), USB Proceedings of 14th International Conference on Modeling Decisions for Artificial Intelligence (MDAI 2017) (pp. 118–131). Kitakyushu, Japan.
      Permanent Research Commons link: https://hdl.handle.net/10289/12344
      Abstract
      Autoencoders learn data representations through reconstruction. Robust training is the key factor affecting the quality of the learned representations and, consequently, the accuracy of the application that use them. Previous works suggested methods for deciding the optimal autoencoder configuration which allows for robust training. Nevertheless, improving the accuracy of a trained autoencoder has got limited, if no, attention. We propose a new approach that improves the accuracy of a trained autoencoder’s results and answers the following question, Given a trained autoencoder, a test image, and using a real-parameter optimizer, can we generate better quality reconstructed image version than the one generated by the autoencoder?. Our proposed approach combines both the decoder part of a trained Resitricted Boltman Machine-based autoencoder with the Competitive Swarm Optimization algorithm. Experiments show that it is possible to reconstruct images using trained decoder from randomly initialized representations. Results also show that our approach reconstructed better quality images than the autoencoder in most of the test cases. Indicating that, we can use the approach for improving the performance of a pre-trained autoencoder if it does not give satisfactory results.
      Date
      2017
      Type
      Conference Contribution
      Collections
      • Computing and Mathematical Sciences Papers [1310]
      Show full item record  

      Usage

      Downloads, last 12 months
      25
       
       

      Usage Statistics

      For this itemFor all of Research Commons

      The University of Waikato - Te Whare Wānanga o WaikatoFeedback and RequestsCopyright and Legal Statement