Using the concepts of information-gap theory, this paper develops a theoretical framework for information-gap uncertainty applied to neural networks, and ...
Abstract—A novel technique for the evaluation of neural net- work robustness against uncertainty using a nonprobabilistic ap- proach is presented.
A novel technique for the evaluation of neural network robustness against uncertainty using a nonprobabilistic approach is presented.
Evaluation of Neural Network Robust Reliability Using Information-Gap Theory. Authors. Pierce, S. Gareth; Ben-Haim, Yakov; Worden, Keith; Manson, Graeme.
A novel technique for the evaluation of neural network robustness against uncertainty using a nonprobabilistic approach is presented.
Evaluation of Neural Network Robust Reliability Using Information-Gap Theory. Pierce, S.G., Ben-Haim, Y., Worden, K., Manson, G.
The main objective of this work is to study the impact of the choice of input uncertainty models on robustness evaluations for probabilities of failure.
People also ask
How robust are deep neural networks?
What does the prediction accuracy of a neural network depend on in deep learning?
Jul 12, 2024 · This paper introduces a fresh perspective on BNN classifier robustness, considering natural input variations while accounting for prediction uncertainties.
PDF | The paper describes a new method based on the information-gap theory which enables an evaluation of worst case error predictions of the kNN method.
The paper describes a new method based on the information-gap theory which enables an evaluation of the mini-models robustness to a specified kind of ...