VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability
M Prabhushankar, G AlRegib - IEEE Journal of Selected Topics …, 2024 - ieeexplore.ieee.org
In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc
visual explanations for neural networks. Predictive uncertainty refers to the variability in the …
visual explanations for neural networks. Predictive uncertainty refers to the variability in the …
Low-Dimensional Gradient Helps Out-of-Distribution Detection
Detecting out-of-distribution (OOD) samples is essential for ensuring the reliability of deep
neural networks (DNNs) in real-world scenarios. While previous research has predominantly …
neural networks (DNNs) in real-world scenarios. While previous research has predominantly …
Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks
M Prabhushankar, G AlRegib - arXiv preprint arXiv:2405.13758, 2024 - arxiv.org
The widespread adoption of deep neural networks in machine learning calls for an objective
quantification of esoteric trust. In this paper we propose GradTrust, a classification trust …
quantification of esoteric trust. In this paper we propose GradTrust, a classification trust …
Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
Y Wu, R Yu, X Cheng, Z He, X Huang - arXiv preprint arXiv:2405.17816, 2024 - arxiv.org
In the open world, detecting out-of-distribution (OOD) data, whose labels are disjoint with
those of in-distribution (ID) samples, is important for reliable deep neural networks (DNNs) …
those of in-distribution (ID) samples, is important for reliable deep neural networks (DNNs) …
Transitional Uncertainty with Layered Intermediate Predictions
In this paper, we discuss feature engineering for single-pass uncertainty estimation. For
accurate uncertainty estimates, neural networks must extract differences in the feature space …
accurate uncertainty estimates, neural networks must extract differences in the feature space …
Intelligent Multi-View Test Time Augmentation
In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed
to enhance the robustness and accuracy of image classification models against viewpoint …
to enhance the robustness and accuracy of image classification models against viewpoint …
Transitional Uncertainty with Intermediate Neural Gaussian Processes
R Benkert, M Prabhushankar, G AlRegib - openreview.net
In this paper, we discuss feature engineering for single-pass uncertainty estimation. For
accurate uncertainty estimates, neural networks must extract differences in the feature space …
accurate uncertainty estimates, neural networks must extract differences in the feature space …
Explainable machine learning for hydrocarbon prospect risking
Hydrocarbon prospect risk assessment is an important process in oil and gas exploration
involving the integrated analysis of various geophysical data modalities, including seismic …
involving the integrated analysis of various geophysical data modalities, including seismic …