Training Trajectories by Continuous Recurrent Multilayer Networks  

Oleh:

Galicki, M. ; Leistritz, L. ; Kochs, E. ; Witte, H.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 13 no. 2 (2002), page 283-291.
Topik: multilayer networks; training trajectories; continuous recurrent; multilayer networks

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.6 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

This paper addresses the problem of training trajectories by means of continuous recurrent neural networks whose feedforward parts are multilayer perceptrons. Such networks can approximate a general non linear dynamic system with arbitrary accuracy. The learning process is transformed into an optimal control framework where the weights are the controls to be determined. A training algorithm based upon a variational formulation of Pontryagin's maximum principle is proposed for such networks. Computer examples demonstrating the efficiency of the given approach are also presented.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali