NDLI: Parallel implementation of partially connected recurrent networks

Content Provider	IEEE Xplore Digital Library
Author	Fung-Yu Young Lai-Wan Chan
Copyright Year	1994
Description	Author affiliation: Dept. of Comput. Sci., Chinese Univ. of Hong Kong, Shatin, Hong Kong (Fung-Yu Young; Lai-Wan Chan)
Abstract	Recurrent neural networks are suitable for solving problems with temporal extent e.g. speech recognition, time series prediction, sequence generation. The biggest problem is, however, its computational complexity during the training process. Using the well-known real time recurrent learning rule of Zipser and William (1989), the training time of each epoch is of order O(n/sup 4/) where n is the total number of hidden units and output units. To cope with this low efficiency, the authors have devised a new network model called the partially connected recurrent network. Using the modified learning rule, the computational complexity of training becomes only O(mn+np), where m is number of outputs and p is the number of external inputs. In addition this new recurrent model is very suitable for running on a regularly connected SIMD parallel computer since each neuron needs only to communicate with those connected to it directly. The authors have verified this idea by implementing both a ring-structured recurrent network and a grid-structured recurrent network on the DECmpp 12000Sx System with 8192 processors. It can be shown that the training time per epoch now increases only linearly, i.e. O(m+n+p), which is a big advantage for solving large scale problems.
Starting Page	2058
Ending Page	2063
File Size	495366
Page Count	6
File Format	PDF
ISBN	078031901X
DOI	10.1109/ICNN.1994.374530
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	1994-06-28
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Concurrent computing Recurrent neural networks Speech recognition Computational complexity Computer science Neurons Large-scale systems Natural languages Shape Computer networks
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Application of fully recurrent neural networks for speech recognition

Recurrent neural network with backpropagation through time for speech recognition

Parallel implementation of partially connected recurrent networks (1994).

Continuous Mandarin speech recognition using hierarchical recurrent neural networks

A parallel planar lattice architecture for competitively inhibited neural network simulation

A novel architecture for modular implementation of neural networks

Speaker identification using Partially Connected Locally Recurrent Probabilistic Neural Networks

Scene image classfying via the Partially Connected Neural Network

Automatic language identification with recurrent neural networks

Parallel implementation of partially connected recurrent networks

Similar Documents

Application of fully recurrent neural networks for speech recognition

Recurrent neural network with backpropagation through time for speech recognition

Parallel implementation of partially connected recurrent networks (1994).

Continuous Mandarin speech recognition using hierarchical recurrent neural networks

A parallel planar lattice architecture for competitively inhibited neural network simulation

A novel architecture for modular implementation of neural networks

Speaker identification using Partially Connected Locally Recurrent Probabilistic Neural Networks

Scene image classfying via the Partially Connected Neural Network

Automatic language identification with recurrent neural networks

Parallel implementation of partially connected recurrent networks