An optimal weight learning machine for handwritten digit image recognition

Authors:
Zhihong Man;Kevin Lee;Dianhui Wang;Zhenwei Cao;Suiyang Khoo
Affiliations:
Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, Melbourne, VIC 3122, Australia;Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, Melbourne, VIC 3122, Australia;Department of Computer Science and Engineering, La Trobe University, Melbourne, VIC 3087, Australia;Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, Melbourne, VIC 3122, Australia;School of Engineering, Deakin University, Geelong, VIC 3122, Australia
Venue:
Signal Processing
Year:
2013

Citing 9
Cited 0

Modern Control Engineering

Modern Control Engineering
Application of Bayesian trained RBF networks to nonlinear time-series modeling

Signal Processing - From signal processing theory to implementation
Letters: Training T-S norm neural networks to refine weights for fuzzy if-then rules

Neurocomputing
A definition of partial derivative of random functions and its application to RBFNN sensitivity analysis

Neurocomputing
Recognition of off-line printed Arabic text using Hidden Markov Models

Signal Processing
Classification of three-way data by the dissimilarity representation

Signal Processing
Neural networks for classification: a survey

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Handwritten digit recognition by neural networks with single-layer training

IEEE Transactions on Neural Networks
Stochastic choice of basis functions in adaptive function approximation and the functional-link net

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.08

Visualization

Abstract

An optimal weight learning machine for a single-hidden layer feedforward network (SLFN) with the application to handwritten digit image recognition is developed in this paper. It is seen that both the input weights and the output weights of the SLFN are globally optimized with the batch learning type of least squares. All feature vectors of the classifier can then be placed at the prescribed positions in the feature space in the sense that the separability of all nonlinearly separable patterns can be maximized, and a high degree of recognition accuracy can be achieved with a small number of hidden nodes in the SLFN. An experiment for the recognition of the handwritten digit image from both the MNIST database and the USPS database is performed to show the excellent performance and effectiveness of the proposed methodology.