Fast Training of Recurrent Networks Based on The EM Algorithm  

Oleh:

Ma, Sheng ; Ji, Chuanyi

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 9 no. 1 (1998), page 11-26.
Topik: ALGORITHM; fast training; networks; EM algorithm

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.3 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

In this work, a probabilistic model is established for recurrent networks. The expectation - maximization (EM) algorithm is then applied to derive a new fast training algorithm for recurrent networks through mean - field approximation. This new algorithm converts training a complicated recurrent network into training an array of individual feedforward neurons. These neurons are then trained via a linear weighted regression algorithm. The training time has been improved by five to 15 times on benchmark problems.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali