arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.06124cs.LG
收藏

孪生神经网络回归是一种半监督回归算法

Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

Perimeter Institute for Theoretical Physics(圆周理论物理研究所);University of Waterloo(滑铁卢大学);National Research Council of Canada(加拿大国家研究委员会);Vector Institute for Artificial Intelligence(向量人工智能研究所)

Sebastian J. Wetzel, Roger G. Melko, Isaac Tamblyn

摘要:

孪生神经网络回归(TNNR)是一种半监督回归算法,只要存在其他标记的锚数据点,它就可以在未标记的数据点上训练。TNNR被训练来预测两个不同数据点的目标值之间的差异,而不是目标本身。通过综合看不见的数据点的目标与所有训练数据点的目标之间的预测差异,可以获得对原始回归问题的非常准确的预测。由于预测差的任何循环的总和应该为零,因此循环可以被提供给训练数据,即使循环内的数据点本身是未标记的。半监督训练显著提高了TNNR的性能,这已经是最先进的了。

英文摘要:

Twin neural network regression (TNNR) is a semi-supervised regression algorithm, it can be trained on unlabelled data points as long as other, labelled anchor data points, are present. TNNR is trained to predict differences between the target values of two different data points rather than the targets themselves. By ensembling predicted differences between the targets of an unseen data point and all training data points, it is possible to obtain a very accurate prediction for the original regression problem. Since any loop of predicted differences should sum to zero, loops can be supplied to the training data, even if the data points themselves within loops are unlabelled. Semi-supervised training improves TNNR performance, which is already state of the art, significantly.

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。

↑