基于Vine Copula的深度模型回溯解算
Retrospective Uncertainties for Deep Models using Vine Copulas
摘要:
尽管深度模型作为学习机器取得了重大进展,但不确定性估计仍然是一个重大挑战。现有的解决方案依赖于修改的损失函数或架构改变。我们建议通过补充任何网络来弥补缺乏内置的不确定性估计,回顾性地,在一个整体复合中,我们称之为Vine-Copula神经网络(VCNN)。通过合成和真实数据实验,我们表明VCNN可以是任务(回归/分类)和架构(循环,完全连接)不可知的,同时提供可靠和更好的校准不确定性估计,与最先进的内置不确定性解决方案相当。
英文摘要:
Despite the major progress of deep models as learning machines, uncertainty estimation remains a major challenge. Existing solutions rely on modified loss functions or architectural changes. We propose to compensate for the lack of built-in uncertainty estimates by supplementing any network, retrospectively, with a subsequent vine copula model, in an overall compound we call Vine-Copula Neural Network (VCNN). Through synthetic and real-data experiments, we show that VCNNs could be task (regression/classification) and architecture (recurrent, fully connected) agnostic while providing reliable and better-calibrated uncertainty estimates, comparable to state-of-the-art built-in uncertainty solutions.
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。