Dynamic thresholds for controlling encoding and retrieval operations in localist (or distributed) neural networks: The need for biologically plausible implementations
Pickering, Alan. 2000. Dynamic thresholds for controlling encoding and retrieval operations in localist (or distributed) neural networks: The need for biologically plausible implementations. Behavioral and Brain Sciences, 23(04), pp. 488-489. ISSN 0140-525X [Article]
No full text availableAbstract or Description
A dynamic threshold, which controls the nature and course of learning, is a pivotal concept in Page's general localist framework. This commentary addresses various issues surrounding biologically plausible implementations for such thresholds. Relevant previous research is noted and the particular difficulties relating to the creation of so-called instance representations are highlighted. It is stressed that these issues also apply to distributed models.
Item Type: |
Article |
||||
Identification Number (DOI): |
|||||
Departments, Centres and Research Units: |
|||||
Dates: |
|
||||
Item ID: |
8505 |
||||
Date Deposited: |
18 Mar 2015 10:20 |
||||
Last Modified: |
04 Jul 2017 10:31 |
||||
Peer Reviewed: |
Yes, this version has been peer-reviewed. |
||||
URI: |
Edit Record (login required) |