The Library
Dimension reduction in recurrent networks by canonicalization
Tools
Tools
Tools
Grigoryeva, Lyudmila and Ortega, Juan-Pablo (2021) Dimension reduction in recurrent networks by canonicalization. Journal of Geometric Mechanics, 13 (4). pp. 647-677. doi:10.3934/jgm.2021028 ISSN 1941-4889.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: http://dx.doi.org/10.3934/jgm.2021028
Abstract
Many recurrent neural network machine learning paradigms can be formulated using state-space representations. The classical notion of canonical state-space realization is adapted in this paper to accommodate semi-infinite inputs so that it can be used as a dimension reduction tool in the recurrent networks setup. The so-called input forgetting property is identified as the key hypothesis that guarantees the existence and uniqueness (up to system isomorphisms) of canonical realizations for causal and time-invariant input/output systems with semi-infinite inputs. Add...
| Item Type: | Journal Article | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Statistics | ||||||||
| Journal or Publication Title: | Journal of Geometric Mechanics | ||||||||
| Publisher: | American Institute of Mathematical Sciences (AIMS) | ||||||||
| ISSN: | 1941-4889 | ||||||||
| Official Date: | 21 December 2021 | ||||||||
| Dates: |
|
||||||||
| Volume: | 13 | ||||||||
| Number: | 4 | ||||||||
| Page Range: | pp. 647-677 | ||||||||
| DOI: | 10.3934/jgm.2021028 | ||||||||
| Status: | Peer Reviewed | ||||||||
| Publication Status: | Published | ||||||||
| Reuse Statement (publisher, data, author rights): | This is a pre-copy-editing, author-produced PDF of an article accepted for publication in [insert journal title] following peer review. The definitive publisher-authenticated version [insert complete citation information here] is available online at: xxxxxxx [insert URL that the author will receive upon publication here]. | ||||||||
| Access rights to Published version: | Restricted or Subscription Access | ||||||||
| Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
