Multi-Valued Autoencoders and Classification of Large-Scale Multi-Class Problem
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 11
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
- EP ID EP240416
- DOI 10.14569/IJACSA.2017.081103
- Views 99
- Downloads 0
Software Cost Estimation using Enhanced Artificial Bee Colony Algorithm
Cost estimation is very important in software development progress so that resource and time planning can be successfully performed. Accurate estimation of cost is directly related to the decision making mechanism in the...
A Novel Approach for Submission of Tasks to a Data Center in a Virtualized Cloud Computing Environment
The submission of tasks to a data center plays a crucial role to achieve the services like scheduling, processing in a cloud computing environment. Energy consumption of a data center must be considered for task processi...
Improved Generalization in Recurrent Neural Networks Using the Tangent Plane Algorithm
The tangent plane algorithm for real time recurrent learning (TPA-RTRL) is an effective online training method for fully recurrent neural networks. TPA-RTRL uses the method of approaching tangent planes to accelerate the...
Deep Learning Approaches for Data Augmentation and Classification of Breast Masses using Ultrasound Images
Breast classification and detection using ultrasound imaging is considered a significant step in computer-aided diagno-sis systems. Over the previous decades, researchers have proved the opportunities to automate the ini...
Development of knowledge Base Expert System for Natural treatment of Diabetes disease
The development of expert system for treatment of Diabetes disease by using natural methods is new information technology derived from Artificial Intelligent research using ESTA (Expert System Text Animation) Syste...