Daniela de Albuquerque

Daniela de Albuquerque

Transitional Year (PGY-1) Resident at MAHEC. Matched into Diagnostic Radiology at University of Washington (Seattle).

Posts by Collection

portfolio

publications

The effects of distraction on brain processes underlying signal detection

Published in Neuropsychologia, 2016

This work leverages the high temporal resolution of EEG to study the neural consequences of a global, continuous distractor on signal-detection processes.

Recommended citation: Demeter, E., DeAlbuquerque, D., & Worldorff, M. (2016). "The Effects of ongoing distraction on the neural processes underlying signal detection." Neuropsychologia. 89(335-343).
Download Paper

Deep Generative Analysis for Task-Based Functional MRI Experiments

Published in Journal of Machine Learning Research, 2021

In this work we follow a Generalized Additive Model (GAM) approach to construct a 3D convolutional VAE capable of more flexibly modeling entire brain volumes, while preserving interpretability.

Recommended citation: De Albuquerque, D., Goffinet, J., Wright, R., & Pearson, J. (2021). "Deep Generative Analysis for Task-Based Functional MRI Experiments." Journal of Machine Learning Research. 149(1-29).
Download Paper

Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models

Published in Proceedings of the 38th Conference on Neural Information Processing Systems, 2024

In this project we exploited a previously established connection between the stochastic and probability flow ordinary differential equations (pfODEs) underlying Diffusion-Based Models (DBMs) to derive a new class of models, inflationary flows, that uniquely and deterministically map high-dimensional data to a lower-dimensional Gaussian distribution via ODE integration.

Recommended citation: De Albuquerque, D., & Pearson, J.(2024). "Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models." In Proceedings of the 38th Conference on Neural Information Processing Systems.
Download Paper

Latent Representation Inference for the Biomedical Sciences Through the Lens of Deep Generative Modeling.

Published in ProQuest Dissertations & Theses Global, 2025

This publication offers a detailed view of my PhD thesis work which focused on creating new deep generative modeling techniques to achieve better representation learning for biomedical data.

Recommended citation: De Albuquerque, D.(2025). "Latent Representation Inference for the Biomedical Sciences Through the Lens of Deep Generative Modeling." Available from ProQuest Dissertations & Theses Global. (3341637296).
Download Paper

Dynamic Compression Flows for Neuroscience Data

Published in Proceedings of the 43rd International Conference on Machine Learning, 2026

In this project we leveraged emerging ideas from the flow-matching literature to construct two jointly-trained flows capable of inferring compressed and identifiable representations from the data, while also capturing temporal dynamics.

Recommended citation: Wei, G.*, De Albuquerque, D.*, Martinez, M., Pan, S. & Pearson, J.(2026). "Dynamic Compression Flows for Neuroscience Data." In Proceedings of the 43rd International Conference on Machine Learning.
Download Paper

talks

teaching

Cardiac Physiology

Graduate/Professional Course, University of Brasilia's School of Medicine, Medical Physiology, 2011

I was a teaching assistant for the graduate cardiac physiology course at University of Brasilia’s School of Medicine (Brazil).

Physics 141L & 142L

Undergraduate course, Duke University, Physics, 2015

I was a teaching assistant for Physics 141L (Classical Mechanics) and 142L (Electricity & Magnetism) for life science undergraduate students at Duke during the summer of 2015. These courses were taught during Summer Sessions I & II and were conducted at Duke’s marine laboratory campus in Beaufort, NC.

ECE682D

Graduate course, Duke University, Electrical and Computer Engineering (ECE), 2023

This is a graduate course on probabilistic machine learning methods cross-listed between ECE, Statistics, and Computer Science (CS). It covers key concepts in prediction and decision theory typically encountered in machine learning and data science, under a more formal statistical framework. For additional details, see course website here. For my work as a TA for this course, I was selected to receive Duke ECE’s outstanding graduate student TA award on Spring 2023!

ECE586

Graduate course, Duke University, Electrical and Computer Engineering (ECE), 2023

This is a graduate course introducing incoming ECE Masters and PhD students to fundamental concepts in logic and set theory, metric spaces, topology, vector spaces, and convex optimization. For additional details see course website here. For my work as a TA for this course, I was selected to receive Duke ECE’s outstanding graduate student TA award on Spring 2024!