|
Title:
|
COMBINING FUZZY DOMINANCE BASED PSO AND GRADIENT DESCENT FOR EFFECTIVE PARAMETER ESTIMATION OF GENE REGULATORY NETWORKS |
|
Author(s):
|
Sanjoy Das , Karim Morcos , Stephen M. Welch |
|
ISBN:
|
978-972-8924-87-4 |
|
Editors:
|
António Palma dos Reis |
|
Year:
|
2009 |
|
Edition:
|
Single |
|
Keywords:
|
PSO, multi-objective, gradient, optimization, genomics, Arabidopsis. |
|
Type:
|
Full Paper |
|
First Page:
|
3 |
|
Last Page:
|
10 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Stochastic optimization techniques such as multi-objective PSO are very useful in determining the parameters of gene
regulatory network models. Unfortunately, evaluating the performance of such a model with a set of parameters is
computationally expensive. The fuzzy ε-dominance based PSO algorithm is a recent approach that is particularly well
suited for these modeling tasks, achieving convergence to the Pareto front with a relatively small number of function
evaluations. In order to further reduce the function evaluations this paper considers ways to incorporates explicit gradient
descent steps within this algorithm. As a case study, the performance of the proposed approach is investigated to compute
the parameters of a differential equation model of Arabidopsis flowering time control. |
|
|
|
|
|
|
