Loading...
Please wait, while we are loading the content...
Similar Documents
Rejection of Incorrect Answers from a Neural Net Classiier Rejection of Incorrect Answers from a Neural Net Classiier
| Content Provider | Semantic Scholar |
|---|---|
| Author | Smieja, Frank J. |
| Copyright Year | 1993 |
| Abstract | The notion of approximator rejection is described, and applied to a neural network. For a real world classiication problem the residual error is shown to decrease with the inverse exponential of the fraction of patterns rejected. The trade-oo of \good" patterns rejected and \bad" patterns rejected is shown to increase approximately linearly with rejection rate. A compromise is therefore necessary between trade-oo/rejection rate and residual error. A meta-level solution is proposed for removal of the residual error, through use of a modular system of parallel approximators. |
| File Format | PDF HTM / HTML |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |