Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/20662
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | AMELOOT, Tom | - |
dc.contributor.author | VAN DEN BUSSCHE, Jan | - |
dc.date.accessioned | 2016-02-16T14:52:14Z | - |
dc.date.available | 2016-02-16T14:52:14Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | NEURAL COMPUTATION, 27 (12), p. 2623-2660 | - |
dc.identifier.issn | 0899-7667 | - |
dc.identifier.uri | http://hdl.handle.net/1942/20662 | - |
dc.description.abstract | We study the expressive power of positive neural networks. The model uses positive connection weights and multiple input neurons. Different behaviors can be expressed by varying the connection weights. We show that in discrete time and in the absence of noise, the class of positive neural networks captures the so-called monotone-regular behaviors, which are based on regular languages. A finer picture emerges if one takes into account the delay by which a monotone-regular behavior is implemented. Each monotone-regular behavior can be implemented by a positive neural network with a delay of one time unit. Some monotone-regular behaviors can be implemented with zero delay. And, interestingly, some simple monotone-regular behaviors cannot be implemented with zero delay. | - |
dc.language.iso | en | - |
dc.publisher | MIT PRESS | - |
dc.rights | © 2015 Massachusetts Institute of Technology | - |
dc.title | Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors | - |
dc.type | Journal Contribution | - |
dc.identifier.epage | 2660 | - |
dc.identifier.issue | 12 | - |
dc.identifier.spage | 2623 | - |
dc.identifier.volume | 27 | - |
local.format.pages | 38 | - |
local.bibliographicCitation.jcat | A1 | - |
dc.description.notes | [Ameloot, Tom J.] Hasselt Univ, B-3500 Hasselt, Belgium. Transnat Univ Limburg, B-3500 Hasselt, Belgium. | - |
local.publisher.place | CAMBRIDGE | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
dc.identifier.doi | 10.1162/NECO_a_00789 | - |
dc.identifier.isi | 000365674700005 | - |
item.fullcitation | AMELOOT, Tom & VAN DEN BUSSCHE, Jan (2015) Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors. In: NEURAL COMPUTATION, 27 (12), p. 2623-2660. | - |
item.contributor | AMELOOT, Tom | - |
item.contributor | VAN DEN BUSSCHE, Jan | - |
item.validation | ecoom 2016 | - |
item.accessRights | Open Access | - |
item.fulltext | With Fulltext | - |
crisitem.journal.issn | 0899-7667 | - |
crisitem.journal.eissn | 1530-888X | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1502.06094.pdf | Non Peer-reviewed author version | 563.16 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.