| dc.creator | Yip, Kenneth | |
| dc.creator | Sussman, Gerald Jay | |
| dc.date | 2004-10-08T20:37:08Z | |
| dc.date | 2004-10-08T20:37:08Z | |
| dc.date | 1997-11-01 | |
| dc.date.accessioned | 2013-10-09T02:46:25Z | |
| dc.date.available | 2013-10-09T02:46:25Z | |
| dc.date.issued | 2013-10-09 | |
| dc.identifier | AIM-1633 | |
| dc.identifier | http://hdl.handle.net/1721.1/6673 | |
| dc.identifier.uri | http://koha.mediu.edu.my:8181/xmlui/handle/1721 | |
| dc.description | Humans rapidly and reliably learn many kinds of regularities and generalizations. We propose a novel model of fast learning that exploits the properties of sparse representations and the constraints imposed by a plausible hardware mechanism. To demonstrate our approach we describe a computational model of acquisition in the domain of morphophonology. We encapsulate phonological information as bidirectional boolean constraint relations operating on the classical linguistic representations of speech sounds in term of distinctive features. The performance model is described as a hardware mechanism that incrementally enforces the constraints. Phonological behavior arises from the action of this mechanism. Constraints are induced from a corpus of common English nouns and verbs. The induction algorithm compiles the corpus into increasingly sophisticated constraints. The algorithm yields one-shot learning from a few examples. Our model has been implemented as a computer program. The program exhibits phonological behavior similar to that of young children. As a bonus the constraints that are acquired can be interpreted as classical linguistic rules. | |
| dc.format | 593039 bytes | |
| dc.format | 557072 bytes | |
| dc.format | application/postscript | |
| dc.format | application/pdf | |
| dc.language | en_US | |
| dc.relation | AIM-1633 | |
| dc.title | Sparse Representations for Fast, One-Shot Learning |
| Files | Size | Format | View |
|---|---|---|---|
|
There are no files associated with this item. |
|||