home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!mcsun!uknet!cam-eng!visakan
- From: visakan@eng.cam.ac.uk (Visakan Kadirkamanathan)
- Newsgroups: comp.ai.neural-nets
- Subject: Paper available
- Message-ID: <1992Dec12.112520.26763@eng.cam.ac.uk>
- Date: 12 Dec 92 11:25:20 GMT
- Sender: anon@eng.cam.ac.uk (placeholder for future)
- Organization: Cambridge University Engineering Department, UK
- Lines: 67
- Nntp-Posting-Host: dsl.eng.cam.ac.uk
-
- The following paper is available via ftp. It is placed in the Cambridge
- University ftp archive svr-ftp.eng.cam.ac.uk. The ftp instructions for
- retrieval follow the summary.
-
- The paper appeared In Proceedings of the Institute of Acoustics, Volume 14,
- Part 6, 1992.
-
- ------------------------------------------------------------------------------
- Application of an architecturally dynamic network for speech
- pattern classification
-
-
- Visakan Kadirkamanathan and Mahesan Niranjan
-
-
- Cambridge University Engineering Department
- Cambridge CB2 1PZ, England
-
-
-
- SUMMARY
-
- We have previously adopted a function estimation approach to the problem of
- sequential learning with neural networks and derived a network that grows with
- increasing observations. This network is a single hidden layer Gaussian radial
- basis function (GaRBF) network with a single output unit. On receiving new
- observation, the network adds a new hidden unit or adapts the existing
- parameters by the Kalman filter.
-
- In this paper, we extend the network to have multiple output units. By
- choosing to adapt only the linear coefficients (hidden - output layer
- weights), considerable memory savings can be achieved for the resulting Kalman
- filter than if the parameters of the basis functions were also adapted.
- Results for this network are presented for the Peterson-Barney vowel
- classification problem in which the
- observations are presented sequentially and only once. The performance is
- comparable to that achieved by some of the standard block estimation methods.
- This approach can also be viewed as an alternate method of arriving at an
- approximate complexity of the network required to solve a given problem,
- eliminating the need for an a priori selection of network size.
-
- ------------------------------------------------------------------------------
-
- FTP INSTRUCTIONS:
-
- unix> ftp svr-ftp.eng.cam.ac.uk
- Name: anonymous
- Password: (your_userid@your_site)
- ftp> cd reports
- ftp> binary
- ftp> get kadirkamanathan_ioa92.ps.Z
- ftp> quit
- unix> uncompress kadirkamanathan_ioa92.ps.Z
- unix>
-
-
- Other related reports placed in the archive are:-
- kadirkamanathan_tr111.ps
- kadirkamanathan_icassp92.ps
-
- ------------------------------------------------------------------------------
-
- --
- Dr.Visakan Kadirkamanathan email: visakan@uk.ac.cam.eng
- Cambridge University Engineering Department
- Trumpington Street, Cambridge CB2 1PZ, UK. Tel : +44 223 332754
- ------------------------------------------------------------------------------
-