Related papers: Interpretable Boosted Decision Tree Analysis for t…

Many machine learning classification tasks involve imbalanced datasets, which are often subject to over-sampling techniques aimed at improving model performance. However, these techniques are prone to generating unrealistic or infeasible…

Trustworthy Artificial Intelligence solutions are essential in today's data-driven applications, prioritizing principles such as robustness, safety, transparency, explainability, and privacy among others. This has led to the emergence of…

Machine learning algorithms are growing increasingly popular in particle physics analyses, where they are used for their ability to solve difficult classification and regression problems. While the tools are very powerful, they may often be…

In machine learning algorithm design, there exists a trade-off between the interpretability and performance of the algorithm. In general, algorithms which are simpler and easier for humans to comprehend tend to show worse performance than…

With the dramatic advances in deep learning technology, machine learning research is focusing on improving the interpretability of model predictions as well as prediction performance in both basic and applied research. While deep learning…

Recent research has recognized interpretability and robustness as essential properties of trustworthy classification. Curiously, a connection between robustness and interpretability was empirically observed, but the theoretical reasoning…

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Multi-layered representation is believed to be the key ingredient of deep neural networks especially in cognitive tasks like computer vision. While non-differentiable models such as gradient boosting decision trees (GBDTs) are the dominant…

We describe how interpretable boosting algorithms based on ridge-regularized generalized linear models can be used to analyze high-dimensional environmental data. We illustrate this by using environmental, social, human and biophysical data…

A salient approach to interpretable machine learning is to restrict modeling to simple models. In the Bayesian framework, this can be pursued by restricting the model structure and prior to favor interpretable models. Fundamentally,…

Artificial intelligence, particularly through recent advancements in deep learning, has achieved exceptional performances in many tasks in fields such as natural language processing and computer vision. In addition to desirable evaluation…

Identification of boosted, hadronically-decaying top quarks is a problem of central importance for physics goals of the Large Hadron Collider. We present a theoretical analysis of top quark tagging, establishing zeroth-order, minimal…

Machine learning tools are commonly used in modern high energy physics (HEP) experiments. Different models, such as boosted decision trees (BDT) and artificial neural networks (ANN), are widely used in analyses and even in the software…

Neutrinoless double beta decay is one of the most powerful tools to set the neutrino mass absolute scale and establish whether the neutrino is a Majorana particle. After a summary of the neutrinoless double beta decay phenomenology, the…

The \MJ\ Collaboration is operating an array of high purity Ge detectors to search for neutrinoless double-beta decay in $^{76}$Ge. The \MJ\ \DEM\ comprises 44.1~kg of Ge detectors (29.7 kg enriched in $^{76}$Ge) split between two modules…

Machine learning algorithms enable advanced decision making in contemporary intelligent systems. Research indicates that there is a tradeoff between their model performance and explainability. Machine learning models with higher performance…

Building a \BBz experiment with the ability to probe neutrino mass in the inverted hierarchy region requires the combination of a large detector mass sensitive to \BBz, on the order of 1-tonne, and unprecedented background levels, on the…

Neutrinoless double-beta (0$\nu\beta\beta$) decay is the most compelling approach to determine the Majorana nature of neutrino and measure effective Majorana neutrino mass. The LEGEND collaboration is aiming to look for 0$\nu\beta\beta$…

The NEXT-100 detector will search for the neutrinoless double beta decay of $^{136}$Xe using an electroluminescent high-pressure xenon gas TPC filled with 100 kg of enriched Xe. An observation of this hypothetical process would establish a…

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…