About: Relating RNN layers with the spectral WFA ranks in sequence modelling

Not logged in : Login

(Sponging disallowed)

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Relating RNN layers with the spectral WFA ranks in sequence modelling Goto Sponge NotDistinct Permalink

An Entity of Type : bibo:AcademicArticle, within Data Space : linkeddata.uriburner.com:28898 associated with source document(s)

Attributes	Values
type	http://eprints.org/ontology/ConferenceItemEPrint http://eprints.org/ontology/EPrint Article Academic Article
seeAlso	HTML Summary of #74240 Relating RNN layers with the spectral WFA ranks in sequence modelling
http://eprints.org/ontology/hasDocument	Relating RNN layers with the spectral WFA ranks in sequence modelling (PDF) Relating RNN layers with the spectral WFA ranks in sequence modelling (Other) Relating RNN layers with the spectral WFA ranks in sequence modelling (Other) Relating RNN layers with the spectral WFA ranks in sequence modelling (Other) Relating RNN layers with the spectral WFA ranks in sequence modelling (Other) Relating RNN layers with the spectral WFA ranks in sequence modelling (Other)
http://eprints.org/ontology/hasSubmitted	Relating RNN layers with the spectral WFA ranks in sequence modelling (PDF)
dc:hasVersion	Relating RNN layers with the spectral WFA ranks in sequence modelling (PDF)
Title	Relating RNN layers with the spectral WFA ranks in sequence modelling
described by	https://demo.openlinksw.com/about/id/entity/https/www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3
Date	2019-05-30
Creator	Farhana Ferdousi Liza Marek Grzes
status	peer reviewed unpublished
abstract	We analyse Recurrent Neural Networks (RNNs) to understand the significance of multiple LSTM layers. We argue that the Weighted Finite-state Automata (WFA) trained using a spectral learning algorithm are helpful to analyse RNNs. Our results suggest that multiple LSTM layers in RNNs help learning distributed hidden states, but have a smaller impact on the ability to learn long-term dependencies. The analysis is based on the empirical results, however relevant theory (whenever possible) was discussed to justify and support our conclusions.
Is Part Of	https://kar.kent.ac.uk/id/repository
Subject	QA76.76 Computer software
list of authors	https://kar.kent.ac.uk/id/eprint/74240#authors
presented at	ACL workshop on Deep Learning and Formal Languages: Building Bridges
is topic of	https://www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/export_kar_RDFN3.n3
is primary topic of	HTML Summary of #74240 Relating RNN layers with the spectral WFA ranks in sequence modelling

Faceted Search & Find service v1.17_git144 as of Jul 26 2024

Alternative Linked Data Documents: iSPARQL | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3331 as of Aug 25 2024, on Linux (x86_64-ubuntu_noble-linux-glibc2.38-64), Single-Server Edition (378 GB total memory, 17 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software