A modular neural network architecture with concept

Authors:
Yi Ding;Qi Feng;Tianjiang Wang;Xian Fu
Affiliations:
Department of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China and Department of Computer Science and Technology, Hubei Normal University, Huangs ...;Department of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China;Department of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China;Department of Computer Science and Technology, Hubei Normal University, Huangshi 435002, China
Venue:
Neurocomputing
Year:
2014

Citing 4
Cited 0

Training MLPs layer by layer using an objective function for internal representations

Neural Networks
An Improved Multi-objective Technique for Fuzzy Clustering with Application to IRS Image Segmentation

EvoWorkshops '09 Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG
Deep, big, simple neural nets for handwritten digit recognition

Neural Computation
Flexible, high performance convolutional neural networks for image classification

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper focuses on the powerful concept of modularity. It is descried how this concept is deployed in natural neural networks on an architectural as well as on a functional level. Furthermore, different approaches for modular neural networks are discussed. By means of these methods, a two-layer modular neural system is introduced. The basic building blocks of the architecture are multilayer perceptions (MP) with the backpropagation (BP) algorithm. This modular network is designed to combine two different approaches of generalization known from connectionist and logical neural networks; this enhances the generalization abilities of the network. Experiments described in this paper show that the architecture is especially useful in solving problems with a large number of input attributes.