Application of the neural network in diagnosis of breast cancer based on levenberg-marquardt algorithm

Abstract

The traditional Back Propagation (referred to as BP) neural network plays a certain auxiliary role in the diagnosis of breast cancer, but the network model easily leads to misdiagnosis when diagnosing breast cancer, and it's easy to fall into the minimum, slow convergence. In order to optimize the network and improve the accuracy, a Levenberg-Marquardt optimization algorithm is suggested in this paper. The simulation is carried out by sample selection and special clinic choice. The experimental results show that the algorithm based on Levenberg-Marquardt optimization has better predictive effect and faster convergence than the BP neural network in breast cancer diagnosis.