DocumentCode :
2456062
Title :
Grayscale image recall from imperfect inputs with a two layer dendritic lattice associative memory
Author :
Urcid, Gonzalo ; Ritter, Gerhard X. ; Valdiviezo-N, Juan-Carlos
Author_Institution :
Opt. Dept., INAOE, Tonantzintla, Mexico
fYear :
2011
fDate :
19-21 Oct. 2011
Firstpage :
261
Lastpage :
266
Abstract :
We present a two layer dendritic auto-associative memory with high rates of perfect recall of exemplar grayscale images distorted by different transformations or corrupted by random noise. The memory is a feedforward network based on dendritic computing employing lattice algebraic operations and is capable of dealing with real valued inputs. A major consequence of this approach is the direct and fast association of perfect or imperfect input patterns with stored associated patterns without any convergence problems.
Keywords :
associative processing; feedforward neural nets; image processing; Imperfect Inputs; convergence problems; dendritic computing; exemplar gray scale image; feedforward network; gray scale image; lattice algebraic operations; two layer dendritic lattice associative memory; Biological neural networks; Gray-scale; Lattices; Neurons; Noise; Noise measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Nature and Biologically Inspired Computing (NaBIC), 2011 Third World Congress on
Conference_Location :
Salamanca
Print_ISBN :
978-1-4577-1122-0
Type :
conf
DOI :
10.1109/NaBIC.2011.6089606
Filename :
6089606
Link To Document :
بازگشت