A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions of the target domain (e.g.\ class overlap), and iii) accurately identifies queries coming out of the target domain and rejects them. We introduce an original combination of Evidential Deep Learning, Neural Processes, and Neural Turing Machines capable of providing all three essential properties mentioned above for total uncertainty quantification. We observe our method on five classification tasks to be the only one that can excel all three aspects of total calibration with a single standalone predictor. Our unified solution delivers an implementation-friendly and compute efficient recipe for safety clearance and provides intellectual economy to an investigation of algorithmic roots of epistemic awareness in deep neural nets.
翻译:具有可靠预测不确定性的概率分类器(i) 成功地符合目标域数据, (ii) 提供目标域困难区域经校准的等级概率(例如/类重叠), (iii) 准确地辨别出目标域以外的问题并予以拒绝。 我们引入了一种原始组合,即“深深层学习证明”、“神经过程”和“神经外观机”,能够提供上述所有三种基本特性,以量化不确定性。 我们观察到,我们在五项分类任务上的方法是唯一能够以单一独立预测器优于全面校准所有三个方面的方法。 我们的统一解决方案提供了一种便于执行的高效安全清理配方,并为调查深神经网中成象意识的算法根源提供了知识经济。