arXiv subjects

Brian Wright

Publications and source records attributed to Brian Wright.

4 recordsLinked to original sources

arXiv2026

Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing

Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We present a controlled head-to-head comparison of two knowledge representations over an identical classroom corpus: (A) vector RAG, replicating the best-performing configuration from our prior study, and (B) an LLM-compiled wiki (Karpathy framework), in which the corpus is synthesized at ingest into linked concept pages with explicit cross-references and citations back to source materials. We evaluate 59 questions spanning single-fact recall, cross-unit concept linking, synthesis and explanation, and currency after a syllabus revision, scored by an LLM judge against a human-authored rubric. Both representations answered single-fact questions about equally well (9.33 vs. 9.96 of 10), but diverged sharply on questions requiring links across course units. The compiled wiki remained accurate and grounded (9.93; 100% grounded in cited sources), while retrieval scored lower and was markedly less grounded (8.14; 64%). The wiki's citations let students and instructors trace any claim back to the lecture that introduced it, adding a layer of dynamic retrieval that machine learning courses require. While further testing is needed, instructors using AI to support learning in ML courses should consider wiki-based structure for its potential to support foundational elements of best practice.

cs.AI↗

arXiv2025

3D Printing as a Rapid Prototyping Approach for Novel RF Cavity Designs

3D-printing of radiofrequency (RF) cavity resonators could provide a cost-effective solution that enables rapid prototyping and design flexibility compared to traditional fabrication of full-metal cavities. In this work, the feasibility of fabrication of a useful multi-mode GHz cavity is explored. Two kinds of plastics, two slicing approaches and two metal coating techniques were used to build a series of clamped cavities with thin inner copper surface on otherwise 3D printed plastic surface. The cavities were then bench-tested to identify spatial field distributions, operating frequencies and quality factors (Q-factor). Pros and cons of the used fabrication approaches were identified and understood, and the performance of longitudinally sliced painted cavity design demonstrated considerable practicality of 3D-printing approach in designing rf systems.

physics.acc-ph↗

arXiv2025

The Future of Data Science Education

The definition of Data Science is a hotly debated topic. For many, the definition is a simple shortcut to Artificial Intelligence or Machine Learning. However, there is far more depth and nuance to the field of Data Science than a simple shortcut can provide. The School of Data Science at the University of Virginia has developed a novel model for the definition of Data Science. This model is based on identifying a unified understanding of the data work done across all areas of Data Science. It represents a generational leap forward in how we understand and teach Data Science. In this paper we will present the core features of the model and explain how it unifies various concepts going far beyond the analytics component of AI. From this foundation we will present our Undergraduate Major curriculum in Data Science and demonstrate how it prepares students to be well-rounded Data Science team members and leaders. The paper will conclude with an in-depth overview of the Foundations of Data Science course designed to introduce students to the field while also implementing proven STEM oriented pedagogical methods. These include, for example, specifications grading, active learning lectures, guest lectures from industry experts and weekly gamification labs.

stat.OT↗

arXiv2022

Optimal Exploration of an Exhaustible Resource with Stochastic Discoveries

The standard Hotelling model assumes that the stock of an exhaustible resource is known. We expand on the model by Arrow and Chang that introduced stochastic discoveries and for the first time completely solve such a model using impulse control. The model has two state variables: the "proven" reserves as well as a finite unexplored area available for exploration with constant marginal cost, resulting in a Poisson process of new discoveries. We prove that a frontier of critical levels of "proven" reserves exists, above which exploration is stopped, and below which it happens at infinite speed. This frontier is increasing in the explored area, and higher "proven" reserve levels along this critical threshold are indicative of more scarcity, not less. In this stochastic generalization of Hotelling's rule, the expected shadow price of reserves rises at the rate of interest across exploratory episodes. However, the actual trajectories of prices realized prior to exhaustion of the exploratory area may jump up or down upon exploration. Conditional on non-exhaustion, expected price arises at a rate bounded above by the rate of interest, consistent with most empirical tests based on observed price histories.

q-fin.MF↗