arXiv subjects

Dana Udwin

Publications and source records attributed to Dana Udwin.

4 recordsLinked to original sources

arXiv2026

What You Read is What You Classify: Highlighting Attributions to Text and Text-Like Inputs

At present, there are no easily understood explainable artificial intelligence (AI) methods for discrete token inputs, like text. Most explainable AI techniques do not extend well to token sequences, where both local and global features matter, because state-of-the-art models, like transformers, tend to focus on global connections. Therefore, existing explainable AI algorithms fail by (i) identifying disparate tokens of importance, or (ii) assigning a large number of tokens a low value of importance. This method for explainable AI for tokens-based classifiers generalizes a mask-based explainable AI algorithm for images. It starts with an Explainer neural network that is trained to create masks to hide information not relevant for classification. Then, the Hadamard product of the mask and the continuous values of the classifier's embedding layer is taken and passed through the classifier, changing the magnitude of the embedding vector but keeping the orientation unchanged. The Explainer is trained for a taxonomic classifier for nucleotide sequences and it is shown that the masked segments are less relevant to classification than the unmasked ones. This method focused on the importance the token as a whole (i.e., a segment of the input sequence), producing a human-readable explanation.

cs.LG↗

arXiv2025

CaTE Data Curation for Trustworthy AI

This report provides practical guidance to teams designing or developing AI-enabled systems for how to promote trustworthiness during the data curation phase of development. In this report, the authors first define data, the data curation phase, and trustworthiness. We then describe a series of steps that the development team, especially data scientists, can take to build a trustworthy AI-enabled system. We enumerate the sequence of core steps and trace parallel paths where alternatives exist. The descriptions of these steps include strengths, weaknesses, preconditions, outcomes, and relevant open-source software tool implementations. In total, this report is a synthesis of data curation tools and approaches from relevant academic literature, and our goal is to equip readers with a diverse yet coherent set of practices for improving AI trustworthiness.

cs.LG↗

arXiv2020

Interpreting Deep Neural Networks Through Variable Importance

While the success of deep neural networks (DNNs) is well-established across a variety of domains, our ability to explain and interpret these methods is limited. Unlike previously proposed local methods which try to explain particular classification decisions, we focus on global interpretability and ask a universally applicable question: given a trained model, which features are the most important? In the context of neural networks, a feature is rarely important on its own, so our strategy is specifically designed to leverage partial covariance structures and incorporate variable dependence into feature ranking. Our methodological contributions in this paper are two-fold. First, we propose an effect size analogue for DNNs that is appropriate for applications with highly collinear predictors (ubiquitous in computer vision). Second, we extend the recently proposed "RelATive cEntrality" (RATE) measure (Crawford et al., 2019) to the Bayesian deep learning setting. RATE applies an information theoretic criterion to the posterior distribution of effect sizes to assess feature significance. We apply our framework to three broad application areas: computer vision, natural language processing, and social science.

stat.ML↗

arXiv2015

R Markdown

Reproducibility is increasingly important to statistical research, but many details are often omitted from the published version of complex statistical analyses. A reader's comprehension is limited to what the author concludes, without exposure to the computational process. Often, the industrious reader cannot expand upon or validate the author's results. Even the author may struggle to reproduce their own results upon revisiting them. R Markdown is an authoring syntax that combines the ease of Markdown with the statistical programming language R. An R Markdown document or presentation interweaves computation, output and written analysis to the effect of transparency, clarity and an inherent invitation to reproduce (especially as sharing data is now as easy as the click of a button). It is an open-source tool that can be used either on its own or through the RStudio integrated development environment (IDE). In addition to facilitating reproducible research, R Markdown is a boon to collaboratively-minded data analysts, whose workflow can be streamlined by sharing only one master document that contains both code and content. Statistics educators may also find that R Markdown is helpful as a homework template, for both ease-of-use and in discouraging students from copy-and-pasting results from classmates. Training students in R Markdown will introduce to the workforce a new class of data analysts with an ingrained, foundational inclination toward reproducible research.

stat.CO↗