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.


page 1

page 2

page 3

page 4


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

Machine learning is increasingly deployed in safety-critical domains whe...

Quantifying Epistemic Uncertainty in Deep Learning

Uncertainty quantification is at the core of the reliability and robustn...

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

Neural networks have revolutionized the field of machine learning with i...

Aleatoric and Epistemic Uncertainty with Random Forests

Due to the steadily increasing relevance of machine learning for practic...

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

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