1 code implementation • 23 Jun 2023 • Kion Fallah, Alec Helbling, Kyle A. Johnsen, Christopher J. Rozell
In this work, we propose a contrastive learning approach that directly models the latent manifold using Lie group operators parameterized by coefficients with a sparsity-promoting prior.
1 code implementation • 1 Apr 2023 • Alec Helbling, Christopher J. Rozell, Matthew O'Shaughnessy, Kion Fallah
Using information from a sequence of query responses, we can estimate user preferences over a set of image attributes and perform preference-guided image editing and generation.
1 code implementation • 7 Jun 2022 • Noga Mudrik, Yenho Chen, Eva Yezerets, Christopher J. Rozell, Adam S. Charles
Learning interpretable representations of neural dynamics at a population level is a crucial first step to understanding how observed neural activity relates to perception and behavior.
2 code implementations • 7 May 2022 • Kion Fallah, Christopher J. Rozell
Sparse coding strategies have been lauded for their parsimonious representations of data that leverage low dimensional structure.
no code implementations • 4 Apr 2021 • Ayse S. Cakmak, Samuel Densen, Gabriel Najarro, Pratik Rout, Christopher J. Rozell, Omer T. Inan, Amit J. Shah, Gari D. Clifford
Objective: Worldwide, heart failure (HF) is a major cause of morbidity and mortality and one of the leading causes of hospitalization.
1 code implementation • 18 Jun 2020 • Marissa C. Connor, Gregory H. Canal, Christopher J. Rozell
This enables us to learn the nonlinear manifold structure from the data and use that structure to define a prior in the latent space.
no code implementations • 31 Aug 2019 • John Lee, Nicholas P. Bertrand, Christopher J. Rozell
The modeling of phenomenological structure is a crucial aspect in inverse imaging problems.
2 code implementations • NeurIPS 2019 • John Lee, Max Dabagia, Eva L. Dyer, Christopher J. Rozell
Our results demonstrate that when clustered structure exists in datasets, and is consistent across trials or time points, a hierarchical alignment strategy that leverages such structure can provide significant improvements in cross-domain alignment.
1 code implementation • 10 May 2019 • Gregory H. Canal, Andrew K. Massimino, Mark A. Davenport, Christopher J. Rozell
Suppose that we wish to estimate a user's preference vector $w$ from paired comparisons of the form "does user $w$ prefer item $p$ or item $q$?," where both the user and items are embedded in a low-dimensional Euclidean space with distances that reflect user and item similarities.
no code implementations • 12 Jun 2018 • Nicholas P. Bertrand, Adam S. Charles, John Lee, Pavel B. Dunn, Christopher J. Rozell
Tracking algorithms such as the Kalman filter aim to improve inference performance by leveraging the temporal dynamics in streaming observations.
no code implementations • 1 Jul 2013 • Adam S. Charles, Han Lun Yap, Christopher J. Rozell
Cortical networks are hypothesized to rely on transient network activity to support short term memory (STM).