Artificial neural networks for flexible manufacturing systems scheduling

Artificial neural networks (ANNs) are information processing systems motivated by the goals of reproducing the cognitive processes and organizational models of neurobiological systems. By virtue of their computational structure, ANN's feature attractive characteristics such as graceful degradation, robust recall with noisy and fragmented data, parallel distributed processing, generalization to patterns outside of the training set, nonlinear modeling capabilities, and learning. These computational features could provide enhanced inferencing functionality and real-time capabilities to develop approaches for traditional difficult problems such as flexible manufacturing system (FMS) scheduling. In this paper three different schemes of ANN's are applied to the FMS scheduling problem. These include a) relaxation-based networks, b) competitive-based schemes, and c) adaptive pattern recognition scheduling.     

An Improved Particle Swarm Optimization for Evolving Feedforward Artificial Neural Networks

This paper presents a new evolutionary artificial neural network (ANN) algorithm named IPSONet that is based on an improved particle swarm optimization (PSO). The improved PSO employs parameter automation strategy, velocity resetting, and crossover and mutations to significantly improve the performance of the original PSO algorithm in global search and fine-tuning of the solutions. IPSONet uses the improved PSO to address the design problem of feedforward ANN. Unlike most previous studies on only using PSO to evolve weights of ANNs, this study puts its emphasis on using the improved PSO to evolve simultaneously structure and weights of ANNs by a specific individual representation and evolutionary scheme. The performance of IPSONet has been evaluated on several benchmarks. The results demonstrate that IPSONet can produce compact ANNs with good generalization ability.     

Making use of population information in evolutionary artificialneural networks

This paper is concerned with the simultaneous evolution of artificial neural network (ANN) architectures and weights. The current practice in evolving ANN's is to choose the best ANN in the last generation as the final result. This paper proposes a different approach to form the final result by combining all the individuals in the last generation in order to make best use of all the information contained in the whole population. This approach regards a population of ANN's as an ensemble and uses a combination method to integrate them. Although there has been some work on integrating ANN modules, little has been done in evolutionary learning to make best use of its population information. Four linear combination methods have been investigated in this paper to illustrate our ideas. Three real-world data sets have been used in our experimental studies, which show that the recursive least-square (RLS) algorithm always produces an integrated system that outperforms the best individual. The results confirm that a population contains more information than a single individual. Evolutionary learning should exploit such information to improve generalization of learned systems.     

A review of genetic algorithms applied to training radial basis function networks

The problems associated with training feedforward artificial neural networks (ANNs) such as the multilayer perceptron (MLP) network and radial basis function (RBF) network have been well documented. The solutions to these problems have inspired a considerable amount of research, one particular area being the application of evolutionary search algorithms such as the genetic algorithm (GA). To date, the vast majority of GA solutions have been aimed at the MLP network. This paper begins with a brief overview of feedforward ANNs and GAs followed by a review of the current state of research in applying evolutionary techniques to training RBF networks.     

Automated learning for reducing the configuration of a feedforwardneural network

In this paper, we present two learning mechanisms for artificial neural networks (ANN's) that can be applied to solve classification problems with binary outputs. These mechanisms are used to reduce the number of hidden units of an ANN when trained by the cascade-correlation learning algorithm (CAS). Since CAS adds hidden units incrementally as learning proceeds, it is difficult to predict the number of hidden units required when convergence is reached. Further, learning must be restarted when the number of hidden units is larger than expected. Our key idea in this paper is to provide alternatives in the learning process and to select the best alternative dynamically based on run-time information obtained. Mixed-mode learning (MM), our first algorithm, provides alternative output matrices so that learning is extended to find one of the many one-to-many mappings instead of finding a unique one-to-one mapping. Since the objective of learning is relaxed by this transformation, the number of learning epochs can be reduced. This in turn leads to a smaller number of hidden units required for convergence. Population-based learning for ANN's (PLAN), our second algorithm, maintains alternative network configurations to select at run time promising networks to train based on error information obtained and time remaining. This dynamic scheduling avoids training possibly unpromising ANNs to completion before exploring new ones. We show the performance of these two mechanisms by applying them to solve the two-spiral problem, a two-region classification problem, and the Pima Indian diabetes diagnosis problem.     

Modifying genetic programming for artificial neural network development for data mining

The development of artificial neural networks (ANNs) is usually a slow process in which the human expert has to test several architectures until he finds the one that achieves best results to solve a certain problem. However, there are some tools that provide the ability of automatically developing ANNs, many of them using evolutionary computation (EC) tools. One of the main problems of these techniques is that ANNs have a very complex structure, which makes them very difficult to be represented and developed by these tools. This work presents a new technique that modifies genetic programming (GP) so as to correctly and efficiently work with graph structures in order to develop ANNs. This technique also allows the obtaining of simplified networks that solve the problem with a small group of neurons. In order to measure the performance of the system and to compare the results with other ANN development methods by means of evolutionary computation (EC) techniques, several tests were performed with problems based on some of the most used test databases in the Data Mining domain. These comparisons show that the system achieves good results that are not only comparable to those of the already existing techniques but, in most cases, improve them.     

Emergence of memory-driven command neurons in evolved artificial agents

Using evolutionary simulations, we develop autonomous agents controlled by artificial neural networks (ANNs). In simple lifelike tasks of foraging and navigation, high performance levels are attained by agents equipped with fully recurrent ANN controllers. In a set of experiments sharing the same behavioral task but differing in the sensory input available to the agents, we find a common structure of a command neuron switching the dynamics of the network between radically different behavioral modes. When sensory position information is available, the command neuron reflects a map of the environment, acting as a location-dependent cell sensitive to the location and orientation of the agent. When such information is unavailable, the command neuron's activity is based on a spontaneously evolving short-term memory mechanism, which underlies its apparent place-sensitive activity. A two-parameter stochastic model for this memory mechanism is proposed. We show that the parameter values emerging from the evolutionary simulations are near optimal; evolution takes advantage of seemingly harmful features of the environment to maximize the agent's foraging efficiency. The accessibility of evolved ANNs for a detailed inspection, together with the resemblance of some of the results to known findings from neurobiology, places evolved ANNs as an excellent candidate model for the study of structure and function relationship in complex nervous systems.     

基于多物种进化遗传算法的神经网络结构学习方法

针对神经网络结构设计的问题及一般结构学习方法的不足,提出了基于多物种进化遗传算法(SEGA),并以MLP为例给出了基于此算法的神经网络结构进化设计方法。该方法融合了遗传算法与神经网络的特点,具有模型搜索空间广泛、算法适应性强的特点。仿真结果表明该方法是有效的。     

Imperfect Evolutionary Systems

In this paper, we propose a change from a perfect paradigm to an imperfect paradigm in evolving intelligent systems. An imperfect evolutionary system (IES) is introduced as a new approach in an attempt to solve the problem of an intelligent system adapting to new challenges from its imperfect environment, with an emphasis on the incompleteness and continuity of intelligence. We define an IES as a system where intelligent individuals optimize their own utility, with the available resources, while adapting themselves to the new challenges from an evolving and imperfect environment. An individual and social learning paradigm (ISP) is presented as a general framework for developing IESs. A practical implementation of the ISP framework, an imperfect evolutionary market, is described. Through experimentation, we demonstrate the absorption of new information from an imperfect environment by artificial stock traders and the dissemination of new knowledge within an imperfect evolutionary market. Parameter sensitivity of the ISP framework is also studied by employing different levels of individual and social learning     

Neural Network Controller against Environment: A Coevolutive approach to Generalize Robot Navigation Behavior

In this paper, a new coevolutive method, called Uniform Coevolution, is introduced to learn weights of a neural network controller in autonomous robots. An evolutionary strategy is used to learn high-performance reactive behavior for navigation and collisions avoidance. The introduction of coevolutive over evolutionary strategies allows evolving the environment, to learn a general behavior able to solve the problem in different environments. Using a traditional evolutionary strategy method, without coevolution, the learning process obtains a specialized behavior. All the behaviors obtained, with/without coevolution have been tested in a set of environments and the capability of generalization is shown for each learned behavior. A simulator based on a mini-robot Khepera has been used to learn each behavior. The results show that Uniform Coevolution obtains better generalized solutions to examples-based problems.