DeepAI AI Chat
Log In Sign Up

Epistemic Deep Learning

The belief function approach to uncertainty quantification as proposed in the Demspter-Shafer theory of evidence is established upon the general mathematical models for set-valued observations, called random sets. Set-valued predictions are the most natural representations of uncertainty in machine learning. In this paper, we introduce a concept called epistemic deep learning based on the random-set interpretation of belief functions to model epistemic learning in deep neural networks. We propose a novel random-set convolutional neural network for classification that produces scores for sets of classes by learning set-valued ground truth representations. We evaluate different formulations of entropy and distance measures for belief functions as viable loss functions for these random-set networks. We also discuss methods for evaluating the quality of epistemic predictions and the performance of epistemic random-set neural networks. We demonstrate through experiments that the epistemic approach produces better performance results when compared to traditional approaches of estimating uncertainty.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/11/2023

Random-Set Convolutional Neural Network (RS-CNN) for Epistemic Deep Learning

Machine learning is increasingly deployed in safety-critical domains whe...
10/23/2021

Quantifying Epistemic Uncertainty in Deep Learning

Uncertainty quantification is at the core of the reliability and robustn...
10/18/2022

An out-of-distribution discriminator based on Bayesian neural network epistemic uncertainty

Neural networks have revolutionized the field of machine learning with i...
01/03/2020

Aleatoric and Epistemic Uncertainty with Random Forests

Due to the steadily increasing relevance of machine learning for practic...
05/26/2021

Epistemic Uncertainty Aware Semantic Localization and Mapping for Inference and Belief Space Planning

We investigate the problem of autonomous object classification and seman...