Interference-less neural network training

Authors:
Ji Hua Ang;Sheng-Uei Guan;Kay Chen Tan;Abdullah Al Mamun
Affiliations:
Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore 117576, Singapore;School of Engineering and Design, Brunel University, Uxbridge, Middlesex, UB8 3PH, UK;Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore 117576, Singapore;Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore 117576, Singapore
Venue:
Neurocomputing
Year:
2008

Citing 14
Cited 3

Numerical recipes in C (2nd ed.): the art of scientific computing

Numerical recipes in C (2nd ed.): the art of scientific computing
Modeling with constructive backpropagation

Neural Networks
Multi-agent reinforcement learning: weighting and partitioning

Neural Networks
Fingerprints classification using artificial neural networks: a combined structural and statistical approach

Neural Networks
Incremental Learning with Respect to New Incoming Input Attributes

Neural Processing Letters
A Fuzzy Approach to Partitioning Continuous Attributes for Classification

IEEE Transactions on Knowledge and Data Engineering
A Dual-Objective Evolutionary Algorithm for Rules Extraction in Data Mining

Computational Optimization and Applications
An evolutionary artificial neural networks approach for breast cancer diagnosis

Artificial Intelligence in Medicine
A constrained-syntax genetic programming system for discovering classification rules: application to medical data sets

Artificial Intelligence in Medicine
Evolutionary computing for knowledge discovery in medical diagnosis

Artificial Intelligence in Medicine
A sequential neural network model for diabetes prediction

Artificial Intelligence in Medicine
A survey of fuzzy logic monitoring and control utilisation in medicine

Artificial Intelligence in Medicine
A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders

Artificial Intelligence in Medicine
Using localizing learning to improve supervised learning algorithms

IEEE Transactions on Neural Networks

Recursive hybrid decomposition with reduced pattern training

International Journal of Hybrid Intelligent Systems
Recursive Learning of Genetic Algorithms with Task Decomposition and Varied Rule Set

International Journal of Applied Evolutionary Computation
Input Space Partitioning for Neural Network Learning

International Journal of Applied Evolutionary Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

The lack of segregation of input space for conventional neural networks (NNs) training often causes interference within the network. The interference-less neural network training (ILNNT) method employed in this paper reduces interference among input attributes by identifying those attributes that interfere with one another and separating them, while attributes that are mutually beneficial are grouped together. Separated attributes in different batches do not share the same hidden neurons while attributes within a batch are connected to the same hidden neurons. ILNNT is applied to widely used benchmark binary and multi-class classification problems and experimental results from K-fold cross validation show that there exist varying degrees of interference among the attributes for the datasets used and the classification accuracy produced by NNs with reduced interference is high.