Multi- Objective Evolutionary Algorithms of Spiking Neural Network - Tapa blanda

Saleh, Abdulrazak Yahya

 
9783330332683: Multi- Objective Evolutionary Algorithms of Spiking Neural Network
Tapa blanda
ISBN 10: 3330332689 ISBN 13: 9783330332683
Editorial: LAP LAMBERT Academic Publishing, 2017

Sinopsis

Spiking neural network (SNN) plays an essential role in classification problems. Although there are many models of SNN, Evolving Spiking Neural Network (ESNN) is widely used in many recent research works. Evolutionary algorithms, mainly differential evolution (DE) have been used for enhancing ESNN algorithm. However, many real-world optimisation problems include several contradictory objectives. Rather than single optimisation, Multi-Objective Optimisation (MOO) can be utilised as a set of optimal solutions to solve these problems.In this book, Harmony Search (HS) and memetic approach were used to improve the performance of MOO with ESNN. Consequently, Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) was applied to improve ESNN structure and accuracy rates. Standard data sets from the UCI machine learning are used for evaluating the performance of this enhanced multi objective hybrid model. The experimental results have proved that the Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) gives better results in terms of accuracy and network structure.

"Sinopsis" puede pertenecer a otra edición de este libro.

Reseña del editor

Spiking neural network (SNN) plays an essential role in classification problems. Although there are many models of SNN, Evolving Spiking Neural Network (ESNN) is widely used in many recent research works. Evolutionary algorithms, mainly differential evolution (DE) have been used for enhancing ESNN algorithm. However, many real-world optimisation problems include several contradictory objectives. Rather than single optimisation, Multi-Objective Optimisation (MOO) can be utilised as a set of optimal solutions to solve these problems.In this book, Harmony Search (HS) and memetic approach were used to improve the performance of MOO with ESNN. Consequently, Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) was applied to improve ESNN structure and accuracy rates. Standard data sets from the UCI machine learning are used for evaluating the performance of this enhanced multi objective hybrid model. The experimental results have proved that the Memetic Harmony Search Multi-Objective Differential Evolution with Evolving Spiking Neural Network (MEHSMODE-ESNN) gives better results in terms of accuracy and network structure.

Biografía del autor

Received MSc in Computer Science at the UST and PhD in Computer Science (Artificial Intelligence) at the University Teknologi Malaysia (UTM). He is interested in cognitive science, brain modelling, spiking neural networks, optimisation methods. His research interest includes data science, big data,deep learning,parallel programming, statistics and IOT.

"Sobre este título" puede pertenecer a otra edición de este libro.

Editorial
LAP LAMBERT Academic Publishing
Año de publicación
2017
Idioma
Inglés
ISBN 10 
3330332689
ISBN 13 
9783330332683
Encuadernación
Tapa blanda
Número de páginas
64
Contacto del fabricante
no disponible
Persona responsable
no disponible