Binary Classification Model Inspired from Quantum Detection Theory

Abstract

Despite its long history, classification is still a subject of extensive research because new application domains require more effective algorithms than the state-of-the-art classification algorithms, which rely on the logical theory of sets, the theory of probability and the algebra of vector spaces. The combination of distinct theoretical frameworks may be the key to making an important step forward toward a stable and significant improvement in classification effectiveness and, to the same extent improved Quantum Mechanics (QM) signal detection. QM may give rise to a new theoretical framework for classification, since it essentially moves the optimal bound of effectiveness beyond the levels made possible by the state-of-the-art classification algorithms. In this paper, we propose a binary classification model inspired by quantum detection theory in an effort to investigate how much benefit it brings as compared to classical models. Our experiments suggest that the improvement in classification effectiveness can be obtained, although the potential of quantum detection can only be partially exploited.