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.
The Design of an Analog Associative Memory Circuit for Applications in High-Dimensional Computing
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).