@inproceedings{74a7875f7b6e46fcaabef46b6ce9fe06,
title = "LEARN++: An incremental learning algorithm for multilayer perceptron networks",
abstract = "We introduce a supervised learning algorithm that gives neural network classification algorithms the capability of learning incrementally from new data without forgetting what has been learned in earlier training sessions. Schapire's (1990) boosting algorithm, originally intended for improving the accuracy of weak learners, has been modified to be used in an incremental learning setting. The algorithm is based on generating a number of hypotheses using different distributions of the training data and combining these hypotheses using a weighted majority voting. This scheme allows the classifier previously trained with a training database, to learn from new data when the original data is no longer available, even when new classes are introduced. Initial results on incremental training of multilayer perceptron networks on synthetic as well as real-world data are presented in this paper.",
author = "R. Polikar and L. Udpa and Udpa, {S. S.} and V. Honavar",
note = "Publisher Copyright: {\textcopyright} 2000 IEEE.; 25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000 ; Conference date: 05-06-2000 Through 09-06-2000",
year = "2000",
doi = "10.1109/ICASSP.2000.860134",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3414--3417",
booktitle = "Design and Implementation of Signal Processing SystemNeural Networks for Signal Processing Signal Processing EducationOther Emerging Applications of Signal ProcessingSpecial Sessions",
address = "United States",
}