|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
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
| ASCII Text | x | ||
| Michael Hüsken, Christian Goerick, "Fast Learning for Problem Classes Using Knowledge Based Network Initialization," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 6, pp. 6619, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 6, 2000. | |||
| BibTex | x | ||
| @article{ 10.1109/IJCNN.2000.859464, author = {Michael Hüsken and Christian Goerick}, title = {Fast Learning for Problem Classes Using Knowledge Based Network Initialization}, journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on}, volume = {6}, year = {2000}, issn = {1098-7576}, pages = {6619}, doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.859464}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Neural Networks, IEEE - INNS - ENNS International Joint Conference on TI - Fast Learning for Problem Classes Using Knowledge Based Network Initialization SN - 1098-7576 SP EP A1 - Michael Hüsken, A1 - Christian Goerick, PY - 2000 KW - problem class KW - neural network KW - adaptability KW - evolutionary algorithm KW - differential equation KW - weight initialization VL - 6 JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on ER - | |||
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.