First-Order Manifold Data Augmentation for Regression Learning
I Kaufman, O Azencot - arXiv preprint arXiv:2406.10914, 2024 - arxiv.org
Data augmentation (DA) methods tailored to specific domains generate synthetic samples
by applying transformations that are appropriate for the characteristics of the underlying data …
by applying transformations that are appropriate for the characteristics of the underlying data …
Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations
To gain insight into the mechanisms behind machine learning methods, it is crucial to
establish connections among the features describing data points. However, these …
establish connections among the features describing data points. However, these …
A Geometric Framework for Adversarial Vulnerability in Machine Learning
B Bell - 2023 - search.proquest.com
This work starts with the intention of using mathematics to understand the intriguing
vulnerability observed by Szegedy et al.(2014) within artificial neural networks. Along the …
vulnerability observed by Szegedy et al.(2014) within artificial neural networks. Along the …
Exact Path Kernels Naturally Decompose Model Predictions
This paper proposes a generalized exact path kernel gEPK which naturally decomposes
model predictions into localized input gradients or parameter gradients. Many cutting edge …
model predictions into localized input gradients or parameter gradients. Many cutting edge …
Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning
I Kaufman, O Azencot - openreview.net
Deep transformer models consistently achieve groundbreaking results on natural language
processing and computer vision problems, among other engineering and scientific domains …
processing and computer vision problems, among other engineering and scientific domains …