Abstract
In this paper, we develop a novel classification algorithm that is based on the integration between competitive learning and the computational power of quantum computing. The proposed algorithm classifies an input into one of two binary classes even if the input pattern is incomplete. We use the entanglement measure after applying unitary operators to conduct the competition between neurons in order to find the winning class based on wining-take-all. The novelty of the proposed algorithm is shown in its application to the quantum computer. Our idea is validated via classifying the state of Reactor Coolant Pump of a Risky Nuclear Power Plant and compared with other quantum-based competitive neural networks model.
Highlights
Quantum neural networks (QNNs) is a research domain that proposes neural network models based on quantum computing postulates [1]
We propose a novel quantum classification model that exploits the superposition property to allow the competition between the neurons by applying the CNOT-gate, between the register of the input pattern and the register that stores prototypes patterns, and applying the quantum
We have proposed a novel algorithm to perform competitive learning which can be implemented in quantum computer
Summary
Quantum neural networks (QNNs) is a research domain that proposes neural network models based on quantum computing postulates [1]. Several researchers proposed various models and algorithms of CANNs that attempt to harness the principles of quantum computing and quantum information theory [1] These algorithms are classified into three main categories. To overcome the defects of the previous models, we exploit the power of quantum computing to propose a novel quantum classifier by harnessing both the superposition and entanglement to implement competitive learning on quantum systems. We propose a novel quantum classification model that exploits the superposition property to allow the competition between the neurons by applying the CNOT-gate, between the register of the input pattern and the register that stores prototypes patterns, and applying the quantum. Due to the proposed classification model harnesses the superposition property of quantum mechanics, it outperforms the classical model in two ways It performs the competition between neurons exponentially faster than classical competitive neural networks.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
