IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 6 Fast Learning for Problem Classes Using Knowledge Based Network Initialization Como, Italy July 24-July 27 ISBN: 0-7695-0619-4
The success of learning as well as the learning speed of an artificial neural network (ANN) strongly depends on the initial weights. If problem or domain specific knowledge exists, it can be transferred to the ANN by means of a special choice of the initial weights. In this paper, we focus on the choice of a set of initial weights, well suited to fast and robust learning of all particular problems out of a class of related problems. Our evolutionary approach particularly considers the learning algorithm in the design of the initial weights. The superior properties of the initial weights resulting from this algorithm are corroborated using a class defined by solving a differential equation with variable boundary conditions.
Index Terms:
problem class, neural network, adaptability, evolutionary algorithm, differential equation, weight initialization
Citation:
Michael Hüsken, Christian Goerick, "Fast Learning for Problem Classes Using Knowledge Based Network Initialization," ijcnn, vol. 6, pp.6619, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 6, 2000 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb