Miles Rusch

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2018-72

May 18, 2018

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-72.pdf

Abstract—An Associative Memory is designed for computing in high-dimensional (HD) vector spaces. The AM is a crucial part of the part of the Vector Symbolic Architecture (VSA), in which data is mapped into a HD vector space while preserving the similarity of data samples. VSA has been used to implement supervised classifiers that learn more quickly than artificial neural networks. The Associative Memory (AM) stores high-dimensional vectors and, given an input vector, searches its contents in parallel for the nearest vector. The AM is similar to a content-addressable memory (CAM), which is a memory system dedicated to searching for a perfect match between the input data and its stored data. Nearest neighbor search is an essential part of VSA classification algorithms. Two AM architectures, one digital and one analog, are designed and compared.

Advisors: Jan M. Rabaey

---

BibTeX citation:

@mastersthesis{Rusch:EECS-2018-72,
    Author= {Rusch, Miles},
    Editor= {Rabaey, Jan M.},
    Title= {The Design of an Analog Associative Memory Circuit for Applications in High-Dimensional Computing},
    School= {EECS Department, University of California, Berkeley},
    Year= {2018},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-72.html},
    Number= {UCB/EECS-2018-72},
    Abstract= {Abstract—An Associative Memory is designed for computing in high-dimensional (HD) vector spaces. The AM is  a crucial part of the part of the Vector Symbolic Architecture (VSA), in which data is mapped into a HD vector space while preserving the similarity of data samples. VSA has been used to implement supervised classifiers that learn more quickly than artificial neural networks. The Associative Memory (AM) stores high-dimensional vectors and, given an input vector, searches its contents in parallel for the nearest vector.  The AM is similar to a content-addressable memory (CAM), which is a memory system dedicated to searching for a perfect match between the input data and its stored data. Nearest neighbor search is an essential part of VSA classification algorithms. Two AM architectures, one digital and one analog, are designed and compared.},
}

EndNote citation:

%0 Thesis
%A Rusch, Miles 
%E Rabaey, Jan M. 
%T The Design of an Analog Associative Memory Circuit for Applications in High-Dimensional Computing
%I EECS Department, University of California, Berkeley
%D 2018
%8 May 18
%@ UCB/EECS-2018-72
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2018/EECS-2018-72.html
%F Rusch:EECS-2018-72