Anda belum login :: 06 Jun 2023 23:28 WIB
Statistical Active Learning in Multilayer Perceptrons
Article from Journal - ilmiah internasional
IEEE Transactions on Neural Networks vol. 11 no. 1 (2000)
Perpustakaan Pusat (Semanggi)
1 (dapat dipinjam: 0)
Lihat Detail Induk
Proposes methods for generating input locations actively in gathering training data, aiming at solving problems unique to muitilayer perceptrons. One of the problems is that optimum input locations, which are calculated deterministically, sometimes distribute densely around the same point and cause local minima in backpropagation training. Two probabilistic active learning methods, which utilize the statistical variance of locations, are proposed to solve this problem. One is parametric active learning and the other is multipoint-search active learning. Another serious problem in applying active learning to multilayer perceptrons is that a Fisher information matrix can be singular, while many methods, including the proposed ones, assume its regularity. A technique of pruning redundant hidden units is proposed to keep the Fisher information matrix regular. Combined with this technique, active learning can be applied stably to multilayer perceptrons. The effectiveness of the proposed methods is demonstrated through computer simulations on simple artificial problems and a real - world problem of color conversion.
Klik untuk menuliskan opini Anda tentang koleksi ini!
Copyright © 2006, 2007
Unika Atma Jaya
, all rights reserved
Process time: 0.03125 second(s)