Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/20662
Title: | Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors | Authors: | AMELOOT, Tom VAN DEN BUSSCHE, Jan |
Issue Date: | 2015 | Publisher: | MIT PRESS | Source: | NEURAL COMPUTATION, 27 (12), p. 2623-2660 | 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. | Notes: | [Ameloot, Tom J.] Hasselt Univ, B-3500 Hasselt, Belgium. Transnat Univ Limburg, B-3500 Hasselt, Belgium. | Document URI: | http://hdl.handle.net/1942/20662 | ISSN: | 0899-7667 | e-ISSN: | 1530-888X | DOI: | 10.1162/NECO_a_00789 | ISI #: | 000365674700005 | Rights: | © 2015 Massachusetts Institute of Technology | Category: | A1 | Type: | Journal Contribution | Validations: | ecoom 2016 |
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 |
SCOPUSTM
Citations
2
checked on Sep 2, 2020
WEB OF SCIENCETM
Citations
5
checked on Oct 14, 2024
Page view(s)
64
checked on Sep 7, 2022
Download(s)
192
checked on Sep 7, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.