Related papers: Tribuo: Machine Learning with Provenance in Java

Ensuring reproducibility of research is an integral part of good scientific practice. One way to support this is through provenance: information about research workflows from data gathering to researchers' sensemaking processes leading to…

ALAMO is a computational methodology for leaning algebraic functions from data. Given a data set, the approach begins by building a low-complexity, linear model composed of explicit non-linear transformations of the independent variables.…

Machine learning (ML) has emerged as a powerful tool for tackling complex regression and classification tasks, yet its success often hinges on the quality of training data. This study introduces an ML paradigm inspired by domain knowledge…

Despite the huge success of Large Language Models (LLMs) in coding assistants like GitHub Copilot, these models struggle to understand the context present in the repository (e.g., imports, parent classes, files with similar names, etc.),…

Model-based reasoning is a central concept in current research into intelligent diagnostic systems. It is based on the assumption that sources of incorrect behavior in technical devices can be located and identified via the existence of a…

In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they…

Machine learning models built on datasets containing discriminative instances attributed to various underlying factors result in biased and unfair outcomes. It's a well founded and intuitive fact that existing bias mitigation strategies…

Machine learning (ML) models are increasingly being used in metrology applications. However, for ML models to be credible in a metrology context they should be accompanied by principled uncertainty quantification. This paper addresses the…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

Model extrapolation to unseen flow is one of the biggest challenges facing data-driven turbulence modeling, especially for models with high dimensional inputs that involve many flow features. In this study we review previous efforts on…

Marketplaces for machine learning (ML) models are emerging as a way for organizations to monetize models. They allow model owners to retain control over hosted models by using cloud resources to execute ML inference requests for a fee,…

Lack of diversity in data collection has caused significant failures in machine learning (ML) applications. While ML developers perform post-collection interventions, these are time intensive and rarely comprehensive. Thus, new methods to…

Modern applications are increasingly driven by Machine Learning (ML) models whose non-deterministic behavior is affecting the entire application life cycle from design to operation. The pervasive adoption of ML is urgently calling for…

Flow-matching models provide a powerful framework for various applications, offering efficient sampling and flexible probability path modeling. These models are characterized by flows with low curvature in learned generative trajectories,…

The majority of data in businesses and industries is stored in tables, databases, and data warehouses. Reasoning with table-structured data poses significant challenges for large language models (LLMs) due to its hidden semantics, inherent…

Modern networks carry increasingly diverse and encrypted traffic types that demand classification techniques beyond traditional port-based and payload-based methods. This tutorial provides a practical, end-to-end guide to building…

Machine Learning is transitioning from an art and science into a technology available to every developer. In the near future, every application on every platform will incorporate trained models to encode data-based decisions that would be…

While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, incremental learning…

Machine learning (ML) has become a commodity in our every-day lives. We routinely ask ML empowered smartphones to suggest lovely food places or to guide us through a strange place. ML methods have also become standard tools in many fields…

The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…