Share Email Print

Proceedings Paper

Embedding of feature space for pattern recognition using quantum computing
Author(s): Tetsuo Hattori; Osamu Matoba; Bahram Javidi
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In order to deal with a general pattern recognition problem by quantum computing, this paper proposes an embedding method that corresponds a feature vector of n-dimensional space Vn to a vector of the surface of Riemann sphere in the n+1 dimensional space Vn+1, keeping the topology among feature vectors. Because the radius of this Riemann sphere is one, the feature vectors are mapped into normalized vectors. This paper shows that multiple linear discriminant functions can be defined to separate two arbitrary clusters that are mapped onto the Riemann sphere in the space Vn+1. This paper also shows that we can define a unitary transformation that computes the signs of values of those multiple linear discriminant functions, in parallel by quantum computing.

Paper Details

Date Published: 1 August 2002
PDF: 8 pages
Proc. SPIE 4732, Photonic and Quantum Technologies for Aerospace Applications IV, (1 August 2002); doi: 10.1117/12.477426
Show Author Affiliations
Tetsuo Hattori, Kagawa Univ. (Japan)
Osamu Matoba, Univ. of Tokyo (Japan)
Bahram Javidi, Univ. of Connecticut (United States)

Published in SPIE Proceedings Vol. 4732:
Photonic and Quantum Technologies for Aerospace Applications IV
Eric Donkor; Michael J. Hayduk; Andrew R. Pirich; Edward W. Taylor; Andrew R. Pirich; Eric Donkor, Editor(s)

© SPIE. Terms of Use
Back to Top