Evolving Complex Neural Networks
نویسندگان
چکیده
Complex networks like the scale-free model proposed by BarabasiAlbert are observed in many biological systems and the application of this topology to artificial neural network leads to interesting considerations. In this paper, we present a preliminary study on how to evolve neural networks with complex topologies. This approach is utilized in the problem of modeling a chemical process with the presence of unknown inputs (disturbance). The evolutionary algorithm we use considers an initial population of individuals with differents scale-free networks in the genotype and at the end of the algorithm we observe and analyze the topology of networks with the best performances. Experimentation on modeling a complex chemical process shows that performances of networks with complex topology are similar to the feed-forward ones but the analysis of the topology of the most performing networks leads to the conclusion that the distribution of input node information affects the network performance (modeling capability).
منابع مشابه
Adaptive Neural Networks, Gene Networks, and Evolutionary Systems – Real and Artificial Evolving Intelligence
The paper presents an integrated approach to building evolving artificial intelligent systems in terms of evolving connectionist systems (ECOS) that capture principles from neural networks, gene interaction networks and evolutionary systems. The ECOS can be used to solve complex problems from computational biology that is illustrated on a simplified gene regulatory network modeling problem. The...
متن کاملRainfall-runoff modelling using artificial neural networks (ANNs): modelling and understanding
In recent years, artificial neural networks (ANNs) have become one of the most promising tools in order to model complex hydrological processes such as the rainfall-runoff process. In many studies, ANNs have demonstrated superior results compared to alternative methods. ANNs are able to map underlying relationship between input and output data without prior understanding of the process under in...
متن کاملA Neural-Group Basis for Evolving and Developing Neural Networks
This work investigates an intermediate abstraction level, that of neural groups, for modelling the development of complex artificial neural networks. Based on Neural Darwinism [5], Displacement Theory [4] and The Neuromeric Model [17], our DEACANN system avoids the complexities of axonal and dendritic growth while maintaining key aspects of cell signalling, competition and cooperation that appe...
متن کاملPrediction of Red Mud Bound-Soda Losses in Bayer Process Using Neural Networks
In the Bayer process, the reaction of silica in bauxite with caustic soda causes the loss of great amount of NaOH. In this research, the bound-soda losses in Bayer process solid residue (red mud) are predicted using intelligent techniques. This method, based on the application of regression and artificial neural networks (AAN), has been used to predict red mud bound-soda losses in Iran Alumina C...
متن کاملUsing Neural Networks with Limited Data to Estimate Manufacturing Cost
Neural networks were used to estimate the cost of jet engine components, specifically shafts and cases. The neural network process was compared with results produced by the current conventional cost estimation software and linear regression methods. Due to the complex nature of the parts and the limited amount of information available, data expansion techniques such as doubling-data and data-cr...
متن کامل