Diese Dissertation betrifft das Lernen in künstlichen neuronalen Netzen und präsentiert einen neuen evolutionären Algorithmus (Network-Weight-based Evolutionary Algorithm, NWEA), der zusätzliche Mechanismen der Natur in Computational Evolution involviert. NWEA ist eine Lernstrategie, die Information über die Position des Individuums im Suchraum, seine Güte und ANN Topologie in dem Modifikationsmechanismus enthält. Der Grundgedanke von NWEA war eine Verhaltensadaptation neben der strukturellen Adaptation durchzuführen und damit die Verbindung zwischen Individuen und Umwelt zu ermöglichen. Der NWEA Modifikationsstrategie nutzt sowohl Genotyp als auch Phänotyp Information im Evolutionsprozess. Genotyp Information ist durch den Ausgabefehler de...
Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful tec...
In this article we present EANT, "Evolutionary Acquisition of Neural Topologies", a method that crea...
International audienceIn general, the topology of Artificial Neural Networks (ANNs) is human-enginee...
Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern clas...
The aim of this thesis is to develop a system that enables autonomous and situated agents to learn a...
Evolutionary computation has been around ever since the late 50s. This thesis aims at elaborate on g...
Learning and evolution are two fundamental forms of adaptation. There has been a great interest in c...
In this contribution we present a novel method, called Evolutionary Acquisition of Neural Topologies...
Parameter adaptation is one of the key research fields in the area of evolutionary computation. In t...
Evolutionary Programming (EP) represents a methodology of Evolutionary Algorithms (EA) in which muta...
A variety of methods have been applied to the architectural configuration and learning or training o...
This thesis addresses the study of evolutionary methods for the synthesis of neural network controll...
Infolge von sinkenden Hardware-Preisen und der zunehmenden Automatisierung wird maschinelles Lernen ...
An ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes ...
Rozwój teorii sztucznych sieci neuronowych, a także pojawienie się nowych, efektywnych narzędzi prog...
Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful tec...
In this article we present EANT, "Evolutionary Acquisition of Neural Topologies", a method that crea...
International audienceIn general, the topology of Artificial Neural Networks (ANNs) is human-enginee...
Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern clas...
The aim of this thesis is to develop a system that enables autonomous and situated agents to learn a...
Evolutionary computation has been around ever since the late 50s. This thesis aims at elaborate on g...
Learning and evolution are two fundamental forms of adaptation. There has been a great interest in c...
In this contribution we present a novel method, called Evolutionary Acquisition of Neural Topologies...
Parameter adaptation is one of the key research fields in the area of evolutionary computation. In t...
Evolutionary Programming (EP) represents a methodology of Evolutionary Algorithms (EA) in which muta...
A variety of methods have been applied to the architectural configuration and learning or training o...
This thesis addresses the study of evolutionary methods for the synthesis of neural network controll...
Infolge von sinkenden Hardware-Preisen und der zunehmenden Automatisierung wird maschinelles Lernen ...
An ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes ...
Rozwój teorii sztucznych sieci neuronowych, a także pojawienie się nowych, efektywnych narzędzi prog...
Neuroevolution, i.e. evolution of artificial neural networks, has recently emerged as a powerful tec...
In this article we present EANT, "Evolutionary Acquisition of Neural Topologies", a method that crea...
International audienceIn general, the topology of Artificial Neural Networks (ANNs) is human-enginee...