Statistical Active Learning in Multilayer Perceptrons  

Oleh:

Fukumizu, K.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 11 no. 1 (2000), page 17-26.
Topik: multilayer networks; statistical; active learning; multilayer perceptrons

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

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.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali