Evolving Complex Neural Networks That Age - Evolutionary Computation, 1995., IEEE International Conference on
نویسندگان
چکیده
The combination of the broad problem searching capabilities of a genetic algorithm with the local maxima location capabilities of a hill climbing algorithm can be a powerful technique for solving classification problems. Producing a number of specialist artificial neural networks, each an expert on one category, can be beneficial when solving problems in which the categories are distinct. This paper describes combining genetic algorithms, hill climbing and sets of specialist artificial neural networks to solve a difficult character recognition problem. It also describes a method by which the effects of a large “elite” sub-population can be counter-balanced by using an aging coefficient in the fitness calculation.
منابع مشابه
Editorial: Welcome To The IEEE Neural Networks Society
I WANT towelcomeyou toournewly formedsociety.On February 17, 2002, the IEEE Neural Networks Council (NNC), publisher of the IEEE TRANSACTIONS ON NEURAL NETWORKS (TNN), the IEEE TRANSACTIONS ON FUZZY SYSTEMS (TFS), and the IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (TEC), became the IEEE Neural Networks Society (NNS). This accomplishment was made possible by the relentless efforts of our ExCo...
متن کاملNeural Networks and Evolutionary Computation. PartII: Hybrid Approaches in the Neurosciences
This paper series focusses on the intersection of neural networks and evolutionary computation. It is addressed to researchers from artificial intelligence as well as
متن کاملNeural Networks and Evolutionary Computation. PartI: Hybrid Approaches in Artificial Intelligence
This paper series focusses on the intersection of neural networks and evolutionary computation. It is addressed to researchers from artificial intelligence as well as
متن کاملEvolving artificial neural networks to combine financial forecasts
We conduct evolutionary programming experiments to evolve artificial neural networks for forecast combination. Using stock price volatility forecast data we find evolved networks compare favorably with a naı̈ve average combination, a least squares method, and a Kernel method on out-of-sample forecasting ability—the best evolved network showed strong superiority in statistical tests of encompassi...
متن کاملEvolutionary Computation For On-Line And Off-Line Parameter Tuning Of Evolving Fuzzy Neural Networksc
This work applies Evolutionary Computation to achieve completely self-adapting Evolving Fuzzy Neural Networks (EFuNNs) for operating in both incremental (on-line) and batch (off-line) modes. EFuNNs belong a class of Evolving Connectionist Systems (ECOS), capable of performing clustering-based, on-line, local area learning and rule extraction. Through EC, its parameters such as learning rates an...
متن کامل