Abstract | ||
---|---|---|
There are some learning problems for which a priori information, such as the Jacobian of mapping, is available in addition to input-output examples. This kind of information can be beneficial in neural network learning if it can be embedded into the network. This article is concerned with the method for learning the mapping and available Jacobian simultaneously. The basic idea is to minimize the c... |
Year | DOI | Venue |
---|---|---|
1997 | 10.1162/neco.1997.9.5.937 | Neural Computation |
Keywords | Field | DocType |
multilayer neural network,hybrid learning,cost function,neural network,computer experiment,input output,backpropagation | Jacobi method,Jacobian matrix and determinant,Computer science,A priori and a posteriori,Algorithm,Learning rule,Artificial intelligence,Artificial neural network,Backpropagation,Hybrid system,Machine learning,Reinforcement learning | Journal |
Volume | Issue | ISSN |
9 | 5 | 0899-7667 |
Citations | PageRank | References |
4 | 1.04 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeong-Woo Lee | 1 | 99 | 27.84 |
Jun-Ho Oh | 2 | 523 | 55.78 |