A Novel Multi-Objective Genetic Algorithm Approach to Artificial Neural Network Topology Optimisation: The Breast Cancer Classification Problem

Bevilacqua, Vitoantonio; Marra, Giuseppe; Menolascina, Filippo; Pannarale, Paolo; Pedone, A.

doi:10.1109/ijcnn.2006.246940

Cited by 49 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mutations, which extract neurons, are executed in neuron number decrease order, similarly as layer addition -in a new layer index decrease order. One of the Clojure [9] benefits over other programming languages is usage of unchangeable data structures -collections and containers, the content of which cannot be changed. In return, while trying to add a new element to the collection the new substance of the collection will be created containing this element.…”

Section: Fig 5 Hidden Layer Neuron Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Structure Optimization Algorithm

Nowakowski¹,

Dorogyy²,

Doroga-Ivaniuk³

2018

JAMRIS

View full text Add to dashboard Cite

This paper presents a deep analysis of literature on the problems of optimization of parameters and structure of the neural networks and the basic disadvantages that are present in the observed algorithms and methods. As a result, there is suggested a new algorithm for neural network structure optimization, which is free of the major shortcomings of other algorithms. The paper describes a detailed description of the algorithm, its implementation and application for recognition problems.

show abstract

Section: Fig 5 Hidden Layer Neuron Extractionmentioning

confidence: 99%

“…Depending on the problem at hand, the selection of the correct activation function allows for faster learning and potentially a more accurate NN. In [9], a GA was used to determine which of several activation functions (linear, logsig, and tansig) were ideal for a breast cancer diagnosis application.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Structure Optimization Algorithm

Nowakowski¹,

Dorogyy²,

Doroga-Ivaniuk³

2018

JAMRIS

View full text Add to dashboard Cite

show abstract

“…More recently, Bevilacqua et al have presented a multi-objective GA (MOGA) approach [7] to search for the optimal network topology. This work has been undertaken since the results obtained with a previous approach [8] demonstrated to be competitive, but the system training proved to be too computation intensive.…”

Section: Moga: Multi-objective Genetic Algorithmmentioning

confidence: 99%

Evolutionary ANNs: A state of the art survey

Azzini

Tettamanzi

2011

Intelligenza Artificiale

View full text Add to dashboard Cite

Neuro-genetic systems have become a very important topic of study in evolutionary computation in recent years. They are models that use evolutionary algorithms to optimize neural network design. This article is a survey of the state of art of evolutionary ANN systems, with a focus on the most recent developments, presented in the literature during the last decade. The main purpose of this work is to provide an update and extension of Yao's milestone survey, published back in 1999, by taking the most recent literature into account.

show abstract

“…Another work carried out by Wang et al (2002), considered the definition of an optimal network that was based on the combination of constructing and pruning by GAs, while, more recently, Bevilacqua et al (2006) presented a multi-objective GA approach to optimize the search for the optimal topology, based on Schema Theory.…”

Section: Architecture Optimizationmentioning

confidence: 99%

Evolutionary Approaches for ANNs Design

Azzini

Tettamanzi

2009

Encyclopedia of Artificial Intelligence

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are computational models, loosely inspired by biological neural networks, consisting of interconnected groups of artificial neurons which process information using a connectionist approach. ANNs are widely applied to problems like pattern recognition, classification, and time series analysis. The success of an ANN application usually requires a high number of experiments. Moreover, several parameters of an ANN can affect the accuracy of solutions. A particular type of evolving system, namely neuro-genetic systems, have become a very important research topic in ANN design. They make up the so-called Evolutionary Artificial Neural Networks (EANNs), i.e., biologicallyinspired computational models that use evolutionary algorithms (EAs) in conjunction with ANNs. Evolutionary algorithms and state-of-the-art design of EANN were introduced first in the milestone survey by Xin Yao (1999), and, more recently, by Abraham (2004), by Cantu-Paz and Kamath (2005), and then by Castellani (2006). The aim of this article is to present the main evolutionary techniques used to optimize the ANN design, providing a description of the topics related to neural network design and corresponding issues, and then, some of the most recent developments of EANNs found in the literature. Finally a brief summary is given, with a few concluding remarks.

show abstract

A Novel Multi-Objective Genetic Algorithm Approach to Artificial Neural Network Topology Optimisation: The Breast Cancer Classification Problem

Cited by 49 publications

References 7 publications

Neural Network Structure Optimization Algorithm

Neural Network Structure Optimization Algorithm

Evolutionary ANNs: A state of the art survey

Evolutionary Approaches for ANNs Design

Contact Info

Product

Resources

About