An Algorithm for Pruning Redundant Modules in Min-Max Modular Network with GZC Function
نویسندگان
چکیده
The min-max modular neural network with Gaussian zerocrossing function (M-GZC) has locally tuned response characteristic and emergent incremental learning ability, but it suffers from quadratic complexity in storage space and response time. Redundant Sample pruning and redundant structure pruning can be considered to overcome these weaknesses. This paper aims at the latter; it analyzes the properties of receptive field in M-GZC network, and then proposes a strategy for pruning redundant modules. Experiments on both structure pruning and integrated with sample pruning are performed. The results show that our algorithm reduces both the size of the network and the response time notably while not changing the decision boundaries.
منابع مشابه
Typical Sample Selection and Redundancy Reduction for Min-Max Modular Network with GZC Function
The min-max modular neural network with Gaussian zerocrossing function (M-GZC) has locally tuned response characteristic and emergent incremental learning ability, but it suffers from high storage requirement. This paper presents a new algorithm, called Enhanced Threshold Incremental Check (ETIC), which can select representative samples from new training data set and can prune redundant modules...
متن کاملAn Algorithm for Pruning Redundant Modules in Min-Max Modular Network
The min-max modular (M) network is a framework that is capable of solving large-scale pattern classification problems in a parallel way. The M network has been successfully applied to several large-scale real-world prblems. When a complex problem is decomposed into a number of separable problems, however, the M network sufferes from its high redundancy of individual modules. This paper proposes...
متن کاملStructure Pruning Strategies for Min-Max Modular Network
The min-max modular network has been shown to be an efficient classifier, especially in solving large-scale and complex pattern classification problems. Despite its high modularity and parallelism, it suffers from quadratic complexity in space when a multiple-class problem is decomposed into a number of linearly separable problems. This paper proposes two new pruning methods and an integrated p...
متن کاملFault Diagnosis for Industrial Images Using a Min-Max Modular Neural Network
This paper presents a new fault diagnosis method for industrial images based on a Min-Max Modular (M) neural network and a Gaussian Zero-Crossing (GZC) function. The most important advantage of the proposed method over existing approaches such as radial-basis function network and support vector machines is that our classifier has locally tuned response characteristics and the misclassification ...
متن کاملPruning Training Samples Using a Supervised Clustering Algorithm
As practical pattern classification tasks are often very-large scale and serious imbalance such as patent classification, using traditional pattern classification techniques in a plain way to deal with these tasks has shown inefficient and ineffective. In this paper, a supervised clustering algorithm based on min-max modular network with Gaussian-zero-crossing function is adopted to prune train...
متن کامل