EQuaTE:基于HCI视觉反馈的高效量子训练引擎
EQuaTE: Efficient Quantum Train Engine for Dynamic Analysis via HCI-based Visual Feedback
摘要:
本文提出了一种高效的量子训练引擎(ESTATE),它是量子机器学习软件的一种新工具,可以绘制梯度方差来检查我们的量子神经网络(QNN)是否落入局部极小值(在QNN中称为贫瘠高原)。这可以通过动态分析来实现,因为量子比特状态的概率是不确定的。此外,我们的EQUIPTE能够进行基于HCI的视觉反馈,因为软件工程师可以通过可视化识别贫瘠的高原;并根据此信息修改QNN。
英文摘要:
This paper proposes an efficient quantum train engine (EQuaTE), a novel tool for quantum machine learning software which plots gradient variances to check whether our quantum neural network (QNN) falls into local minima (called barren plateaus in QNN). This can be realized via dynamic analysis due to undetermined probabilistic qubit states. Furthermore, our EQuaTE is capable for HCI-based visual feedback because software engineers can recognize barren plateaus via visualization; and also modify QNN based on this information.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。