Sparse distributed memory: Difference between revisions

Revision as of 20:06, 3 November 2011

Revision as of 20:07, 3 November 2011

Line 29:

At the University of Memphis, Uma Ramamurthy, Sidney K. D’Mello, and Stan Franklin created a modified version of the Sparse Distributed Memory system that mathematically represents "realizing forgetting." It uses a decay equation to better show interference in data. The Sparse Distributed Memory system distributes each pattern into approximately one hundredth of the locations, so interference can have detrimental results. <ref name=memphis>{{cite web|title=Realizing Forgetting in a Modified Sparse Distributed Memory System|url=http://csjarchive.cogsci.rpi.edu/proceedings/2006/docs/p1992.pdf|work=Computer Science Department & The Institute for Intelligent Systems|publisher=The University of Memphis|accessdate=1 November 2011|coauthors=Uma Ramamurthy, Sidney K. D’Mello, Stan Franklin|archiveurl=http://csjarchive.cogsci.rpi.edu/proceedings/2006/|archivedate=2006|page=1992|pages=1992-1997}}</ref>

Two possible examples of decay from this modified Sparse Distributed Memory are presented [[Image:Exponential_Decay_Function.png|thumb|320px|right|The exponential decay function]]

'''Exponential Decay Mechanism''': <math>\!f(x)=1+e^{-ax}</math> [[Image:Exponential_Decay_Function.png|thumb|320px|right|The exponential decay function]]

'''Negated-Translated Sigmoid Decay Mechanism''': <math>f(x)=1-[\frac{1}{1+e^{-a(x-c)}}]</math>