Title:
自動的ニューラルネットモデル発生及びメインテナンス
Document Type and Number:
Japanese Patent JP2005523534
Kind Code:
A
Abstract:
Method of incrementally forming and adaptively updating a neural net model are provided. A function approximation node is incrementally added to the neural net model. Function parameters for the function approximation node are determined and function parameters of other nodes in the neural network model are updated, by using the function parameters of the other nodes prior to addition of the function approximation node to the neural network model.
More Like This:
| WO/1996/012221 | DEVICE FOR THE AUTONOMOUS GENERATION OF USEFUL INFORMATION |
| WO/2011/093925 | METHOD AND APPARATUS OF TEXT CLASSIFICATION |
| JPH0348314 | OPTICAL NEURAL NETWORK CIRCUIT |
Inventors:
Men, Tso
Yurt, yo-han
Yurt, yo-han
Application Number:
JP2003586833A
Publication Date:
August 04, 2005
Filing Date:
April 15, 2003
Export Citation:
Assignee:
Computer Associates Sink, Inc.
International Classes:
G06E1/00; G06N3/08; G06N; (IPC1-7): G06N3/08
Attorney, Agent or Firm:
Masaaki Kobashi