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 reject 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 three image classification benchmarks to consistently improve the in-domain uncertainty quantification, out-of-domain detection, and robustness against input data corruption with one single model. Our unified solution delivers an implementation-friendly and computationally 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。 我们引进了一种原始组合,即能提供上述所有三种基本属性的深深层证据学习、神经过程和神经外向机,以量化全部不确定性。 我们观察了三种图像分类基准的方法,以不断改进内部不确定性的量化、外部探测和稳健性,以单一模式防止输入数据腐败。 我们的统一解决方案为安全清理提供了一种便于执行的、符合计算效率的配方,并为深神经网内认知的算法根源调查提供了知识经济。