Random High-Dimensional Binary Vectors, Kernel Methods, and Hyperdimensional Computing

Data Science Seminar

Nicholas Marshall (Oregon State University)


This talk explores the mathematics underlying hyperdimensional computing (HDC), a computing paradigm that employs high-dimensional binary vectors. In HDC, data is encoded by permuting and combining random high-dimensional binary vectors in various ways. We study the affinity structure of HDC and establish a connection to kernel methods.

Start date
Tuesday, March 12, 2024, 1:25 p.m.
End date
Tuesday, March 12, 2024, 2:25 p.m.

Lind Hall 325 and Zoom

Zoom registration