BriefGPT.xyz
Feb, 2020
集成分布蒸馏的通用框架
A general framework for ensemble distribution distillation
HTML
PDF
Jakob Lindqvist, Amanda Olmin, Fredrik Lindsten, Lennart Svensson
TL;DR
通过构建神经网络集成,可以更好地进行预测和不确定性估计,并将不确定性分解为数据不确定性和模型不确定性。本文提出了一种保持神经网络集成分解性质的蒸馏框架,其预测性能与标准蒸馏相当。
Abstract
ensembles
of
neural networks
have been shown to give better performance than single networks, both in terms of predictions and
uncertainty estima
→