Related papers: Interpretable Boosted Decision Tree Analysis for t…

We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition…

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the…

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

The Majorana Demonstrator is an ultra-low background physics experiment searching for the neutrinoless double beta decay of $^{76}$Ge. The Majorana Parts Tracking Database is used to record the history of components used in the construction…

Fairness and interpretability play an important role in the adoption of decision-making algorithms across many application domains. These requirements are intended to avoid undesirable group differences and to alleviate concerns related to…

Unbiased assessment of the predictivity of models learnt by supervised machine-learning methods requires knowledge of the learned function over a reserved test set (not used by the learning algorithm). The quality of the assessment depends,…

The search for neutrinoless double beta decay is a very active field in which the number of proposals for next-generation experiments has proliferated. In this paper we attempt to address both the sense and the sensitivity of such…

This work focuses on plant leaf disease classification and explores three crucial aspects: adversarial training, model explainability, and model compression. The models' robustness against adversarial attacks is enhanced through adversarial…

Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally used to quickly produce models with reasonably high accuracy.…

In this review, we examine the problem of designing interpretable and explainable machine learning models. Interpretability and explainability lie at the core of many machine learning and statistical applications in medicine, economics,…

The MAJORANA Collaboration will seek neutrinoless double beta decay (0nbb) in 76Ge using isotopically enriched p-type point contact (PPC) high purity Germanium (HPGe) detectors. A tonne-scale array of HPGe detectors would require background…

The GERmanium Detector Array GERDA experiment, located at the Laboratori Nazionali del Gran Sasso (LNGS) of INFN, searches for $0\nu\beta\beta$ of $^{76}$Ge. Germanium diodes enriched to $\sim 86~\%$ in the double beta emitter $^{76}$Ge…

The field of machine learning has seen tremendous progress in recent years, with deep learning models delivering exceptional performance across a range of tasks. However, these models often come at the cost of interpretability, as they…

The Majorana nature of massive neutrinos will be crucially probed in the next-generation experiments of the neutrinoless double-beta ($0\nu 2\beta$) decay. The effective mass term of this process, $\langle m\rangle^{}_{ee}$, may be…

Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human…

The MAJORANA DEMONSTRATOR is an array of natural and enriched high purity germanium detectors that will search for the neutrinoless double-beta decay of 76-Ge and perform a search for weakly interacting massive particles (WIMPs) with masses…

The MAJORANA DEMONSTRATOR was a search for neutrinoless double-beta decay ($0\nu\beta\beta$) in the $^{76}$Ge isotope. It was staged at the 4850-foot level of the Sanford Underground Research Facility (SURF) in Lead, SD. The experiment…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

This paper describes methods for comparative evaluation of the interpretability of models of high dimensional time series data inferred by unsupervised machine learning algorithms. The time series data used in this investigation were logs…

Uplift modeling comprises a collection of machine learning techniques designed for managers to predict the incremental impact of specific actions on customer outcomes. However, accurately estimating this incremental impact poses significant…