arXiv subjects

Ryan Lopez

Publications and source records attributed to Ryan Lopez.

4 recordsLinked to original sources

arXiv2026

Active learning for photonic crystals

Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with uncertainty-driven sample selection to accelerate photonic band gap prediction. We employ an analytic LL-BNN formulation, corresponding to the infinite Monte Carlo sample limit, to obtain uncertainty estimates that are strongly correlated with the true predictive error on unlabeled candidate structures. These uncertainty scores drive an active learning strategy that prioritizes the most informative simulations during training. Applied to the task of predicting band gap sizes in two-dimensional, two-tone photonic crystals, our approach achieves up to a 2.7x reduction on average in required training data compared to a random sampling baseline while maintaining predictive accuracy. The efficiency gains arise from concentrating computational resources on high uncertainty regions of the design space rather than sampling uniformly. Given the substantial cost of full band structure simulations, especially in three dimensions, this data efficiency enables rapid and scalable surrogate modeling. Our results suggest that analytic LL-BNN based active learning can substantially accelerate topological optimization and inverse design workflows for photonic crystals, and more broadly, offers a general framework for data efficient regression across scientific machine learning domains.

physics.optics↗

arXiv2025

A Practical SAFE-AI Framework for Small and Medium-Sized Enterprises Developing Medical Artificial Intelligence Ethics Policies

Artificial intelligence (AI) offers incredible possibilities for patient care, but raises significant ethical issues, such as the potential for bias. Powerful ethical frameworks exist to minimize these issues, but are often developed for academic or regulatory environments and tend to be comprehensive but overly prescriptive, making them difficult to operationalize within fast-paced, resource-constrained environments. We introduce the Scalable Agile Framework for Execution in AI (SAFE-AI) designed to balance ethical rigor with business priorities by embedding ethical oversight into standard Agile-based product development workflows. The framework emphasizes the early establishment of testable acceptance criteria, fairness metrics, and transparency metrics to manage model uncertainty, while also promoting continuous monitoring and re-evaluation of these metrics across the AI lifecycle. A core component of this framework are responsibility metrics using scenario-based probability analogy mapping designed to enhance transparency and stakeholder trust. This ensures that retraining or tuning activities are subject to lightweight but meaningful ethical review. By focusing on the minimum necessary requirements for responsible development, our framework offers a scalable, business-aligned approach to ethical AI suitable for organizations without dedicated ethics teams.

cs.CY↗

arXiv2022

GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductions

We develop data-driven methods incorporating geometric and topological information to learn parsimonious representations of nonlinear dynamics from observations. The approaches learn nonlinear state-space models of the dynamics for general manifold latent spaces using training strategies related to Variational Autoencoders (VAEs). Our methods are referred to as Geometric Dynamic (GD) Variational Autoencoders (GD-VAEs). We learn encoders and decoders for the system states and evolution based on deep neural network architectures that include general Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and other architectures. Motivated by problems arising in parameterized PDEs and physics, we investigate the performance of our methods on tasks for learning reduced dimensional representations of the nonlinear Burgers Equations, Constrained Mechanical Systems, and spatial fields of Reaction-Diffusion Systems. GD-VAEs provide methods that can be used to obtain representations in manifold latent spaces for diverse learning tasks involving dynamics.

cs.LG↗

arXiv2020

Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems

We develop data-driven methods for incorporating physical information for priors to learn parsimonious representations of nonlinear systems arising from parameterized PDEs and mechanics. Our approach is based on Variational Autoencoders (VAEs) for learning from observations nonlinear state space models. We develop ways to incorporate geometric and topological priors through general manifold latent space representations. We investigate the performance of our methods for learning low dimensional representations for the nonlinear Burgers equation and constrained mechanical systems.

cs.LG↗