EVIDENTIAL TURING PROCESSES

Melih Kandemir, Abdullah Akgül, Manuel Haussmann, Gozde Unal

Araştırma sonucu: ???type-name???Yazıbilirkişi

2 Atıf (Scopus)

Özet

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.

Orijinal dilİngilizce
Yayın durumuYayınlandı - 2022
Etkinlik10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online
Süre: 25 Nis 202229 Nis 2022

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???10th International Conference on Learning Representations, ICLR 2022
ŞehirVirtual, Online
Periyot25/04/2229/04/22

Bibliyografik not

Publisher Copyright:
© 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

Parmak izi

EVIDENTIAL TURING PROCESSES' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Alıntı Yap