BriefGPT.xyz
May, 2016
量子启发张量网络的监督学习
Supervised Learning with Quantum-Inspired Tensor Networks
HTML
PDF
E. Miles Stoudenmire, David J. Schwab
TL;DR
本研究探讨了如何使用张量网络来优化矩阵积态，以用于分类图像的模型参数化，且在 MNIST 数据集上取得了不到 1% 的测试集分类误差。此外，我们讨论了张量网络形式如何为学习模型提供附加结构，并提出了可能的生成性解释。
Abstract
tensor networks
are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to
→