- Title
- The Law of Practice and localist neural network models
- Creator
- Heathcote, Andrew; Brown, Scott
- Relation
- Behavioral and Brain Sciences Vol. 23, Issue 4, p. 479-480
- Relation
- http://journals.cambridge.org/action/displayAbstract?fromPage=online&aid=65541
- Publisher
- Cambridge University Press
- Resource Type
- journal article
- Date
- 2000
- Description
- An extensive survey by Heathcote et al. (in press) found that the Law of Practice is closer to an exponential than a power form. We show that this result is hard to obtain for models using leaky competitive units when practice affects only the input, but that it can be accommodated when practice affects shunting self-excitation.
- Subject
- Law of Practice; neural network models
- Identifier
- http://hdl.handle.net/1959.13/931285
- Identifier
- uon:11031
- Identifier
- ISSN:0140-525X
- Language
- eng
- Full Text
- Hits: 2659
- Visitors: 3273
- Downloads: 392
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | ATTACHMENT01 | Publisher version (open access) | 52 KB | Adobe Acrobat PDF | View Details Download |