Random-Set Neural Networks (RS-NN)

Machine learning is increasingly deployed in safety-critical domains where robustness against adversarial attacks is crucial and erroneous predictions could lead to potentially catastrophic consequences. This highlights the need for learning systems to be equipped with the means to determine a model...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Manchingal, Shireen Kudukkil, Mubashar, Muhammad, Wang, Kaizheng, Shariatmadar, Keivan, Cuzzolin, Fabio
Format: Article
Language:English
Subjects:
Artificial neural networks
Deep learning
Epistemology
Machine learning
Neural networks
Robustness (mathematics)
Safety critical
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning is increasingly deployed in safety-critical domains where robustness against adversarial attacks is crucial and erroneous predictions could lead to potentially catastrophic consequences. This highlights the need for learning systems to be equipped with the means to determine a model's confidence in its prediction and the epistemic uncertainty associated with it, 'to know when a model does not know'. In this paper, we propose a novel Random-Set Neural Network (RS-NN) for classification. RS-NN predicts belief functions rather than probability vectors over a set of classes using the mathematics of random sets, i.e., distributions over the power set of the sample space. RS-NN encodes the 'epistemic' uncertainty induced in machine learning by limited training sets via the size of the credal sets associated with the predicted belief functions. Our approach outperforms state-of-the-art Bayesian (LB-BNN, BNN-R) and Ensemble (ENN) methods in a classical evaluation setting in terms of performance, uncertainty estimation and out-of-distribution (OoD) detection on several benchmarks (CIFAR-10 vs SVHN/Intel-Image, MNIST vs FMNIST/KMNIST, ImageNet vs ImageNet-O) and scales effectively to large-scale architectures such as WideResNet-28-10, VGG16, Inception V3, EfficientNetB2, and ViT-Base.
ISSN:2331-8422