Multi-objective cooperative coevolution of artificial neural networks (multi-objective cooperative networks)
نویسندگان
چکیده
In this paper we present a cooperative coevolutive model for the evolution of neural network topology and weights, called MOBNET. MOBNET evolves subcomponents that must be combined in order to form a network, instead of whole networks. The problem of assigning credit to the subcomponents is approached as a multi-objective optimization task. The subcomponents in a cooperative coevolutive model must fulfill different criteria to be useful, these criteria usually conflict with each other. The problem of evaluating the fitness on an individual based on many criteria that must be optimized together can be approached as a multi-criteria optimization problems, so the methods from multi-objective optimization offer the most natural way to solve the problem. In this work we show how using several objectives for every subcomponent and evaluating its fitness as a multi-objective optimization problem, the performance of the model is highly competitive. MOBNET is compared with several standard methods of classification and with other neural network models in solving four real-world problems, and it shows the best overall performance of all classification methods applied. It also produces smaller networks when compared to other models. The basic idea underlying MOBNET is extensible to a more general model of coevolutionary computation, as none of its features are exclusive of neural networks design. There are many applications of cooperative coevolution that could benefit from the multi-objective optimization approach proposed in this paper.
منابع مشابه
Pareto Optimization of Two-element Wing Models with Morphing Flap Using Computational Fluid Dynamics, Grouped Method of Data handling Artificial Neural Networks and Genetic Algorithms
A multi-objective optimization (MOO) of two-element wing models with morphing flap by using computational fluid dynamics (CFD) techniques, artificial neural networks (ANN), and non-dominated sorting genetic algorithms (NSGA II), is performed in this paper. At first, the domain is solved numerically in various two-element wing models with morphing flap using CFD techniques and lift (L) and drag ...
متن کاملOptimal Power Management to Minimize SER in Amplify and-Forward Relay Networks
This paper studies optimal power allocation to minimize symbol error rate (SER) of amplify-and-forward cooperative diversity networks. First, we analytically solve optimal power allocation problem to minimize SER for three different scenarios, namely, multi-branch single-relay, single-branch multi-relay and multi-branch multi-relay cooperative diversity networks, all subject to a given total re...
متن کاملAttack-Aware Cooperative Spectrum Sensing in Cognitive Radio Networks under Byzantine Attack
Cooperative Spectrum Sensing (CSS) is an effective approach to overcome the impact of multi-path fading and shadowing issues. The reliability of CSS can be severely degraded under Byzantine attack, which may be caused by either malfunctioning sensing terminals or malicious nodes. Almost, the previous studies have not analyzed and considered the attack in their models. The present study introduc...
متن کاملUsing Neural Networks and Genetic Algorithms for Modelling and Multi-objective Optimal Heat Exchange through a Tube Bank
In this study, by using a multi-objective optimization technique, the optimal design points of forced convective heat transfer in tubular arrangements were predicted upon the size, pitch and geometric configurations of a tube bank. In this way, the main concern of the study is focused on calculating the most favorable geometric characters which may gain to a maximum heat exchange as well as a m...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neural networks : the official journal of the International Neural Network Society
دوره 15 10 شماره
صفحات -
تاریخ انتشار 2002