Evidential Turing Processes

06/02/2021
by   Melih Kandemir, et al.
0

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 and two neural net architectures to consistently give competitive or superior scores with respect to multiple uncertainty quantification metrics against state-of-the-art methods explicitly tailored to one or a few of them. 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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 8

page 16

08/24/2020

SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

Uncertainty quantification is a fundamental yet unsolved problem for dee...
11/08/2021

Uncertainty Quantification in Neural Differential Equations

Uncertainty quantification (UQ) helps to make trustworthy predictions ba...
06/07/2021

BayesIMP: Uncertainty Quantification for Causal Data Fusion

While causal models are becoming one of the mainstays of machine learnin...
12/29/2020

Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification

Uncertainty and confidence have been shown to be useful metrics in a wid...
11/16/2020

Fast Uncertainty Quantification for Deep Object Pose Estimation

Deep learning-based object pose estimators are often unreliable and over...
04/13/2022

Better Uncertainty Quantification for Machine Translation Evaluation

Neural-based machine translation (MT) evaluation metrics are progressing...
11/25/2020

Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval

Uncertainty quantification in image retrieval is crucial for downstream ...

Code Repositories

EvidentialCalibration

Evidential Calibration


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.