A Post-Training Approach for Mitigating Overfitting in Quantum Convolutional Neural Networks

arXiv:2309.01829v2 Announce Type: replace-cross
Abstract: Quantum convolutional neural network (QCNN), an early application for quantum computers in the NISQ era, has been consistently proven successful as a machine learning (ML) algorithm for several tasks with significant accuracy. Derived from its classical counterpart, QCNN is prone to overfitting. Overfitting is a typical shortcoming of ML models that are trained too closely to the availed training dataset and perform relatively poorly on unseen datasets for a similar problem. In this work we …

abstract accuracy algorithm application arxiv computers convolutional neural network convolutional neural networks cs.lg machine machine learning network networks neural network neural networks nisq overfitting quant-ph quantum quantum computers tasks training type