2021/06/02 by Melih Kandemir, Kandemir, Melih, Abdullah Akgül +7
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #cs.LG
paper · pdf · doi:10.48550/arxiv.2106.01216
accepted at ICLR2022; camera ready version
openalex publication_date 2021/06/02 · arxiv created 2022/03/08 · arxiv updated 2022/03/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
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.