Abstract | ||
---|---|---|
The ability to identify and reason about novel aspects of their input would greatly enhance the capabilities of artificial
neural networks. The extent of the novelty could be used to judge the appropriateness of individual networks for the task
to be performed. The location and shape of novel features could be employed to identify the unusual components of the input
and to choose an appropriate response.
|
Year | DOI | Venue |
---|---|---|
1992 | 10.1007/978-1-4615-3192-0_9 | NIPS |
Keywords | Field | DocType |
input reconstruction reliability estimation,artificial neural network | ENCODE,Computer science,Reconstruction error,Artificial intelligence,Perceptron,Machine learning | Conference |
ISBN | Citations | PageRank |
1-55860-274-7 | 8 | 16.19 |
References | Authors | |
4 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dean Pomerleau | 1 | 1039 | 283.23 |