Document Detail


Parallel Programmable Asynchronous Neighborhood Mechanism for Kohonen SOM Implemented in CMOS Technology.
MedLine Citation:
PMID:  22049367     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
We present a new programmable neighborhood mechanism for hardware implemented Kohonen self-organizing maps (SOMs) with three different map topologies realized on a single chip. The proposed circuit comes as a fully parallel and asynchronous architecture. The mechanism is very fast. In a medium sized map with several hundreds neurons implemented in the complementary metal-oxide semiconductor 0.18 μm technology, all neurons start adapting the weights after no more than 11 ns. The adaptation is then carried out in parallel. This is an evident advantage in comparison with the commonly used software-realized SOMs. The circuit is robust against the process, supply voltage and environment temperature variations. Due to a simple structure, it features low energy consumption of a few pJ per neuron per a single learning pattern. In this paper, we discuss different aspects of hardware realization, such as a suitable selection of the map topology and the initial neighborhood range, as the optimization of these parameters is essential when looking from the circuit complexity point of view. For the optimal values of these parameters, the chip area and the power dissipation can be reduced even by 60% and 80%, respectively, without affecting the quality of learning.
Authors:
Rafał Długosz; Marta Kolasa; Witold Pedrycz; Michał Szulc
Related Documents :
488207 - A supernormal period in central axons following single cell stimulation.
19320057 - Dopamine depletion induced up-regulation of hcn3 enhances rebound excitability of basal...
17946407 - A new 3d finite element model of extracellular action potentials recording with a micro...
8238467 - Reduced ionic conductance in turtle brain.
16696357 - Tinnitus and brain activation: insights from transcranial magnetic stimulation.
19964297 - High efficiency electrodes for deep brain stimulation.
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2011-10-28
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  -     ISSN:  1941-0093     ISO Abbreviation:  -     Publication Date:  2011 Oct 
Date Detail:
Created Date:  2011-11-3     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Mobility Timing for Agent Communities, a Cue for Advanced Connectionist Systems.
Next Document:  Scale and Rotation Invariant Local Binary Pattern Using Scale-Adaptive Texton and Sub-uniform Based ...