Multi-Valued Autoencoders and Classification of Large-Scale Multi-Class Problem

Abstract

Two-layered neural networks are well known as autoencoders (AEs) in order to reduce the dimensionality of data. AEs are successfully employed as pre-trained layers of neural networks for classification tasks. Most of the existing studies conceived real-valued AEs in real-valued neural networks. This study investigated complex- and quaternion-valued AEs for complex- and quaternion-valued neural networks. Inputs, weights, biases, and outputs in complex-valued AE (CAE) are complex variables, whereas those in quaternion-valued AE (QAE) are quaternions. In both methods, a split-type activation function is used in the hidden and output units. To deal with the images using the proposed methods, pairs of pixels are allotted to complex-valued inputs in the CAE and quartets of pixels are allotted to quaternion-valued inputs in the QAE. Proposed autoencoders are tested and performance compared with conventional AE for several tasks which are encoding/decoding, handwritten numeral recognition and large-scale multi-class classification. Proposed CAE and QAE revealed as good recognition methods for the tasks and outperformed conventional AE with significance performance in case of large-scale multi-class images recognition.

Authors and Affiliations

Ryusuke Hata, M. A. H. Akhand, Kazuyuki Murase

Keywords

Related Articles

Context-Aware Mobile Application Task Offloading to the Cloud

One of the benefits of mobile cloud computing is the ability to offload mobile applications to the cloud for many reasons including performance enhancement and reduced resource consumption. This paper is concerned with o...

 An Intelligent Software Workflow Process Design for Location Management on Mobile Devices

  Advances in the technologies of networking, wireless communication and trimness of computers lead to the rapid development in mobile communication infrastructure, and have drastically changed information proc...

MapReduce Programs Simplification using a Query Criteria API

A Hadoop HDFS is an organized and distributed collection of files. It is created to store a huge part of data and then retrieve it and analyze it efficiently in a less amount of time. To retrieve and analyze data from th...

Time-Dependence in Multi-Agent MDP Applied to Gate Assignment Problem

Many disturbances can impact gate assignments in daily operations of an airport. Gate Assignment Problem (GAP) is the main task of an airport to ensure smooth flight-to-Gate assignment managing all disturbances. Or, flig...

Method for Psychological Status Estimation by Gaze Location Monitoring Using Eye-Based Human- Computer Interaction

Method for psychological status estimation by gaze location monitoring using Eye-Based Human-Computer Interaction: EBHCI is proposed. Through the experiment with English book reading of e-learning content, relation betwe...

Download PDF file
  • EP ID EP240416
  • DOI 10.14569/IJACSA.2017.081103
  • Views 103
  • Downloads 0

How To Cite

Ryusuke Hata, M. A. H. Akhand, Kazuyuki Murase (2017). Multi-Valued Autoencoders and Classification of Large-Scale Multi-Class Problem. International Journal of Advanced Computer Science & Applications, 8(11), 19-26. https://europub.co.uk/articles/-A-240416