Practical Optoelectronic Neural Network Realization Based on The Fault Tolerance of The Backpropagation Algorithm  

Oleh:

Curtis, K. M. ; Allen, T.J. ; Orton, J. W. ; Hung, Keng-Shen

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 7 no. 2 (1996), page 488-500.
Topik: ALGORITHM; optoelectronic; neural network; tolereance; backpropagation; algorith

Ketersediaan

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

Lihat Detail Induk

Isi artikel

This paper describes how the fault tolerance of the backpropagation algorithm can be used to accommodate the realistic (nonideal) transfer characteristics of the optical communication links used, between neural layers, in optoelectronic neural networks. In particular the authors demonstrate that networks, utilizing MSM (metal - semiconductor - metal) photodiodes (PDs) and either LED (light emitting diode) or MQW (multiple quantum well) laser transmitters within these intraneural links, are capable of performing satisfactorily even in the presence of such nonideal device phenomena as : 60 % optical crosstalk, 50 % optoelectronic device variation, or a thresholded (Ith = 0.5 * Imax) laser output characteristic. Subsequent to this, the authors then show how it is possible to use this fault tolerance to simplify the neuron architecture, to the extent that it consists only of MSM PD s a current amplifier, and an MQW laser. The overall neuron transfer function is then a first - order approximation to the original sigmoidal function.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali