Application of fractional theory in quantum back propagation neural network
Yumin Dong, Xiang Li, Jinlei Zhang, Ziyi Li, Dong Hou
Abstract
In this paper, by applying the theory of fractional calculus to quantum back propagation (BP) neural network, a quantum BP algorithm based on the definition of fractional Grünwald–Letnikoff (G‐L) is proposed. We choose the Sigmoid linear superposition function to replace the activation function of the traditional neural network to construct a fractional quantum BP neural network structure. Experimental results prove that this algorithm improves the convergence speed of the network and reduces the convergence error.
Topics & Concepts
MathematicsArtificial neural networkConvergence (economics)Sigmoid functionBackpropagationQuantumFunction (biology)Superposition principleFractional calculusAlgorithmConstruct (python library)Applied mathematicsComputer scienceMathematical analysisArtificial intelligenceQuantum mechanicsPhysicsEvolutionary biologyBiologyEconomic growthEconomicsProgramming languageAdvanced Sensor and Control SystemsAdvanced Algorithms and ApplicationsAdvanced Adaptive Filtering Techniques