LMS Learning Algorithms : Misconceptions and New Results on Converence  

Oleh:

Wang, Zi-Qin ; Manry, M. T. ; Schiano, J. L.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 11 no. 1 (2000), page 47-56.
Topik: algorithms; LMS; learning algorithms; misconceptions; converence

Ketersediaan

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

Lihat Detail Induk

Isi artikel

The Widrow - Hoff delta rule is one of the most popular rules used in training neural networks. It was originally proposed for the ADALINE, but has been successfully applied to a few nonlinear neural networks as well. Despite its popularity, there exist a few misconceptions on its convergence properties. We consider repetitive learning (i. e., a fixed set of samples are used for training) and provide an in-depth analysis in the least mean square (LMS) framework. Our main result is that contrary to common belief, the nonbatch Widrow - Hoff rule does not converge in general. It converges only to a limit cycle.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali