NDLI: Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting

Content Provider	IEEE Xplore Digital Library
Author	Albesano, D. Gemello, R. Laface, P. Mana, F. Scanzio, S.
Copyright Year	2006
Description	Author affiliation: Loquendo SpA, Torino (Albesano, D.; Gemello, R.)
Abstract	In connectionist learning, one relevant problem is "catastrophic forgetting" that may occur when a network, trained with a large set of patterns, has to learn new input patterns, or has to be adapted to a different environment. The risk of catastrophic forgetting is particularly high when a network is adapted with new data that do not adequately represent the knowledge included in the original training data. Two original solutions are proposed to reduce the risk that the network focuses on new data only, loosing its generalization capability. The first one, conservative training, is a variant to the target assignment policy, while the second approach, support vector rehearsal, selects from the training set the patterns that lay near the borders of the classes not included in the adaptation set. These patterns are used as sentinels that try to keep unchanged the original boundaries of these classes. Moreover, we investigated the extension of the classical approach consisting in applying linear transformations not only to the input features, but also to the outputs of the internal layers. The motivation is that the outputs of an internal layer represent a projection of the input pattern into a space where it should be easier to learn the classification or transformation expected at the output of the network. We illustrate the problems using an artificial test-bed, and apply our techniques to a set of adaptation tasks in the domain of automatic speech recognition (ASR) based on artificial neural networks. Supervised ASR adaptation experiments with several corpora and for different adaptation types are described. We report on the adaptation potential of different techniques, and on the generalization capability of the adapted networks. The results show that the combination of the proposed approaches mitigates the catastrophic forgetting effects, and always outperforms the use of the classical transformations in the feature space.
Starting Page	1554
Ending Page	1561
File Size	375586
Page Count	8
File Format	PDF
ISBN	0780394909
DOI	10.1109/IJCNN.2006.246618
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2006-07-16
Publisher Place	Canada
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Artificial neural networks Automatic speech recognition Training data Electronic mail Automatic testing Backpropagation
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

Fast speaker adaptation of artificial neural networks for automatic speech recognition

Corrective training of hidden control neural network

Vowel and consonant recognition in Turkish using neural networks toward continuous speech recognition

Adapting hybrid ann/hmm to speech variations (2006).

Adapting hybrid ann/hmm to speech variations.

Unsupervised language model adaptation

On the use of neural networks for automatic vowel recognition

Generalization accuracy of probabilistic neural networks compared with backpropagation networks

Application oriented automatic structuring of time-delay neural networks for high performance character and speech recognition

Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting

Similar Documents

Fast speaker adaptation of artificial neural networks for automatic speech recognition

Corrective training of hidden control neural network

Vowel and consonant recognition in Turkish using neural networks toward continuous speech recognition

Adapting hybrid ann/hmm to speech variations (2006).

Adapting hybrid ann/hmm to speech variations.

Unsupervised language model adaptation

On the use of neural networks for automatic vowel recognition

Generalization accuracy of probabilistic neural networks compared with backpropagation networks

Application oriented automatic structuring of time-delay neural networks for high performance character and speech recognition

Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting