The Self-Trapping Attractor Neural Network - Part 1 : Analysis of A Simple 1-D Model  

Oleh:

Pavloski, R. ; Karimi, M.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: IEEE Transactions on Neural Networks vol. 14 no. 1 (Jan. 2003), page 58-65.
Topik: networks; coupled systems feedback; associative memory; attractor neural networks; AAN; connectivity; hopfield model

Ketersediaan

Perpustakaan Pusat (Semanggi) Nomor Panggil: II36.8 Non-tandon: 1 (dapat dipinjam: 0) Tandon: tidak ada

Lihat Detail Induk

Isi artikel

Attractor neural networks (ANN s) based on the Ising model are naturally fully connected and are homogeneous in structure. These features permit a deep understanding of the underlying mechanism, but limit the applicability of these models to the brain. A more biologically realistic model can be derived from an equally simple physical model by utilizing recurrent self - trapping inputs to supplement very sparse intranetwork interactions. This paper reports the analysis of a one - dimensional (1 - D) ANN coupled to a second system that computes overlaps with a single stored memory. Results show that : 1) the 1 - D self - trapping model is equivalent to an isolated ANN with both full connectivity of one strength and nearest neighbor synapses of an independent strength; 2) the dynamics of ANN and self - trapping updates are independent ; 3) there is a critical synaptic noise level below which memory retrieval occurs ; 4) the 1 - D self - trapping model converges to a fully connected Hopfield model for zero strength nearest neighbor synapses, and has a greater magnitude memory overlap for non zero strength nearest neighbor synapses ; and (5) the mechanism of self - trapping is an iterative map on the mean overlap as a function of the reentrant input.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali