1210.6626 (Michael Siomau)

Quantum Perceptron    [PDF]

Michael Siomau

The idea of information encoding on quantum bearers and its quantum-mechanical processing has revolutionized our world and brought mankind on the verge of new enigmatic era of quantum technologies. Inspired by this idea, in present paper we begin the search for advantages of quantum information processing in the field of machine learning. We show that the simplest learning machine -- perceptron -- can dramatically increase its learning capabilities, if operates according to the laws of quantum mechanics. Exploiting only basic properties of the Hilbert space, superposition principle of quantum mechanics and quantum measurements to introduce a quantum perceptron, we demonstrate, for instance, that it is able to learn an arbitrary (Boolean) logical function, while this learning task can not be performed by its classical counterpart.

View original: http://arxiv.org/abs/1210.6626