Incremental Communication for Multilayer Neural Networks : Error Analysis  

Oleh:

Bhavsar, V. C. ; Ghorbani, A. A.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 9 no. 1 (1998), page 68-82.
Topik: multilayer networks; incremental; communication; multilayer; neural networks; error analysis

Ketersediaan

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

Lihat Detail Induk

Isi artikel

Artificial neural networks (ANN s) involve a large amount of internode communications. To reduce the communication cost as well as the time of learning process in ANNs, we earlier proposed (1995) an incremental internode communication method. In the incremental communication method, instead of communicating the full magnitude of the output value of a node, only the increment or decrement to its previous value is sent to a communication link. In this paper, the effects of the limited precision incremental communication method on the convergence behaviour and performance of multilayer neural networks are investigated. The non linear aspects of representing the incremental values with reduced (limited) precision for the commonly used error backpropagation training algorithm are analyzed. It is shown that the nonlinear effect of small perturbations in the input(s) / output of a node does not cause instability. The analysis is supported by simulation studies of two problems. The simulation results demonstrate that the limited precision errors are bounded and do not seriously affect the convergence of multilayer neural networks.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali