Treffer: Recurrent Neural Network for Non-Smooth Convex Optimization Problems with Application to the Identification of Genetic Regulatory Networks

Title:
Recurrent Neural Network for Non-Smooth Convex Optimization Problems with Application to the Identification of Genetic Regulatory Networks
Authors:
LONG CHENG, HOU, Zeng-Guang, YINGZI LIN, MIN TAN, ZHANG, Wenjun Chris, WU, Fang-Xiang
Source:
IEEE transactions on neural networks. 22(5):714-726
Publisher Information:
New York, NY: Institute of Electrical and Electronics Engineers, 2011.
Publication Year:
2011
Physical Description:
print, 46 ref
Original Material:
INIST-CNRS
Subject Terms:
Electronics, Electronique, Computer science, Informatique, Psychology, psychopathology, psychiatry, Psychologie, psychopathologie, psychiatrie, Sciences exactes et technologie, Exact sciences and technology, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Intelligence artificielle, Artificial intelligence, Connexionnisme. Réseaux neuronaux, Connectionism. Neural networks, Sciences biologiques et medicales, Biological and medical sciences, Sciences biologiques fondamentales et appliquees. Psychologie, Fundamental and applied biological sciences. Psychology, Biologie moleculaire et cellulaire, Molecular and cellular biology, Génétique moléculaire, Molecular genetics, Expression génique, Gene expression, Biologie moléculaire, Molecular biology, Biología molecular, Contrainte inégalité, Inequality constraint, Constreñimiento desigualdad, Contrainte égalité, Equality constraint, Constreñimiento igualdad, Expression génique, Gene expression, Expresión genética, Fonction objectif, Objective function, Función objetivo, Gène régulateur, Regulator gene, Gen regulador, Inégalité, Inequality, Desigualdad, Lagrangien, Lagrangian, Lagrangiano, Méthode pénalité, Penalty method, Método penalidad, Point col, Saddle point, Punto silla, Point équilibre, Equilibrium point, Punto equilibrio, Programmation convexe, Convex programming, Programación convexa, Programmation mathématique, Mathematical programming, Programación matemática, Programmation non convexe, Non convex programming, Programación no convexa, Réseau neuronal récurrent, Recurrent neural nets, Réseau neuronal, Neural network, Red neuronal, Solution optimale, Optimal solution, Solución óptima, Convex, genetic regulatory network, identification, non-smooth optimization problem, recurrent neural network
Document Type:
Fachzeitschrift Article
File Description:
text
Language:
English
Author Affiliations:
Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Mechanical and Industrial Engineering Department, College of Engineering, Northeastern University, Boston, MA 02115, United States
Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, Canada
ISSN:
1045-9227
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=24162339
Rights:
Copyright 2015 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems

Molecular and cell biology
Accession Number:
edscal.24162339
Database:
PASCAL Archive

Weitere Informationen

A recurrent neural network is proposed for solving the non-smooth convex optimization problem with the convex inequality and linear equality constraints. Since the objective function and inequality constraints may not be smooth, the Clarke's generalized gradients of the objective function and inequality constraints are employed to describe the dynamics of the proposed neural network. It is proved that the equilibrium point set of the proposed neural network is equivalent to the optimal solution of the original optimization problem by using the Lagrangian saddle-point theorem. Under weak conditions, the proposed neural network is proved to be stable, and the state of the neural network is convergent to one of its equilibrium points. Compared with the existing neural network models for non-smooth optimization problems, the proposed neural network can deal with a larger class of constraints and is not based on the penalty method. Finally, the proposed neural network is used to solve the identification problem of genetic regulatory networks, which can be transformed into a non-smooth convex optimization problem. The simulation results show the satisfactory identification accuracy, which demonstrates the effectiveness and efficiency of the proposed approach.