International Journal on Soft Computing ( IJSC ): August 2018

Thursday, 30 August 2018

MARKOV CHAIN AND ADAPTIVE PARAMETER SELECTION ON PARTICLE SWARM OPTIMIZER

MARKOV CHAIN AND ADAPTIVE PARAMETER SELECTION ON PARTICLE SWARM OPTIMIZER

Chao-Wei Chou, Jiann-Horng Lin* and Rong Jeng Department of Information Management I-Shou University, Kaohsiung 840, Taiwan {choucw, jhlin, rjeng}@isu.edu.tw *Corresponding author , E-mail address: jhlin@isu.edu.tw

ABSTRACT

Particle Swarm Optimizer (PSO) is such a complex stochastic process so that analysis on the stochastic behavior of the PSO is not easy. The choosing of parameters plays an important role since it is critical in the performance of PSO. As far as our investigation is concerned, most of the relevant researches are based on computer simulations and few of them are based on theoretical approach. In this paper, theoretical approach is used to investigate the behavior of PSO. Firstly, a state of PSO is defined in this paper, which contains all the information needed for the future evolution. Then the memory-less property of the state defined in this paper is investigated and proved. Secondly, by using the concept of the state and suitably dividing the whole process of PSO into countable number of stages (levels), a stationary Markov chain is established. Finally, according to the property of a stationary Markov chain, an adaptive method for parameter selection is proposed.

KEYWORDS

Markov chain, Memory-less property, Order Statistics, Particle Swarm Optimizer, Percentile, Stationary Markov chain

Original Source URL : http://airccse.org/journal/ijsc/papers/4213ijsc01.pdf

http://airccse.org/journal/ijsc/current2013.html

Friday, 24 August 2018

International Journal on Soft Computing ( IJSC )

ISSN: 2229 - 6735 [Online] ; 2229 - 7103 [Print]

http://airccse.org/journal/ijsc/ijsc.html

Wednesday, 22 August 2018

A SURVEY OF SPIKING NEURAL NETWORKS AND SUPPORT VECTOR MACHINE PERFORMANCE BYUSINGGPU’S

A SURVEY OF SPIKING NEURAL NETWORKS AND SUPPORT VECTOR MACHINE PERFORMANCE BYUSINGGPU’S

Israel Tabarez-Paz1 , Neil Hernández-Gress2 and Miguel González Mendoza2 . 1Universidad Autónomadel Estado de México Blvd. Universitario s/n, Predio San Javier Atizapán de Zaragoza, México 2 Tecnológico de Monterrey, Campus Estado de México, CarreteraLago de Guadalupe km 3.5 Atizapán de Zaragoza Col. Margarita Maza de Juarez, Atizapán de Zaragora, México

ABSTRACT

In this paper we study the performance of Spiking Neural Networks (SNN)and Support Vector Machine (SVM) by using a GPU, model GeForce 6400M. Respect to applications of SNN, the methodology may be used for clustering, classification of databases, odor, speech and image recognition..In case of methodology SVM, is typically applied for clustering, regression and progression. According to particular characteristics of these methodologies,theycan be parallelizedin several grades. However, level of parallelism is limited to architecture of hardware. So, is very sure to get better results using other hardware with more computational resources. The different approaches are evaluated by the training speed and performance. On the other hand, some authors have coded algorithms SVM light, but nobody has programming QP SVM in a GPU. Algorithms were coded by authors in the hardware, like Nvidia card, FPGA or sequential circuits that depends on methodology used, to compare learning timewith between GPU and CPU. Also, in the survey we introduce a brief description of the types of ANN and its techniques of execution to be related with results of researching.

KEYWORDS

GPU,Spiking Neural Networks, Support Vector Machines, pattern recognition.

Original Source URL : http://airccse.org/journal/ijsc/papers/4313ijsc01.pdf

http://airccse.org/journal/ijsc/current2013.html