Deterministic Nonmonotone Strategies for Effective Training of Multilayer Perceptrons  

Oleh:

Plagianakos, V. P. ; Magoulas, G. D. ; Vrahatis, M. N.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 13 no. 6 (2002), page 1268-1284.
Topik: multilayer networks; deterministic; non monotone; stratefies; training; multilayer

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.7A Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

We present deterministic non monotone learning strategies for multilayer perceptrons (MLP s), i. e., deterministic training algorithms in which error function values are allowed to increase at some epochs. To this end, we argue that the current error function value must satisfy a non monotone criterion with respect to the maximum error function value of the M previous epochs, and we propose a subprocedure to dynamically compute M. The non monotone strategy can be incorporated in any batch training algorithm and provides fast, stable, and reliable learning. Experimental results in different classes of problems show that this approach improves the convergence speed and success percentage of first - order training algorithms and alleviates the need for fine - tuning problem - depended heuristic parameters.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali