Rather than predicting perceptual distortions, one needs to solve the inverse problem: What is the best stimulus to generate a desired visual percept?
Galen Pogoncheff
(he/him)
PhD Student
Computer Science
University of California, Santa Barbara
Galen Pogoncheff joined the Bionic Vision Lab in 2022 as a PhD student in the Computer Science department. Driven to improve the processing of visual stimuli for bionic vision devices, he aims to advance techniques in computer vision using mechanisms inspired by neural processing.
Prior to joining the lab, Galen obtained his B.S. and M.S. in Computer Science from the University of Colorado and subsequently led the research and development of machine learning models for wearable electrophysiology devices at a local startup.
- 3201C BioEngineering
- galenpogoncheff@ucsb.edu
Education
-
MS in Computer Science, 2020
University of Colorado, Boulder
-
BS in Computer Science, 2018
University of Colorado, Boulder
Project Lead
Project Affiliate
Predicting Visual Outcomes for Visual Prostheses
What do visual prosthesis users see, and why? Clinical studies have shown that the vision provided by current devices differs substantially from normal sight.
Publications
Explaining V1 properties with a biologically constrained deep learning architecture
We systematically incorporated neuroscience-derived architectural components into CNNs to identify a set of mechanisms and architectures that comprehensively explain neural activity in V1.
Galen Pogoncheff, Jacob Granley, Michael Beyeler arXiv:2305.11275
Explainable machine learning predictions of perceptual sensitivity for retinal prostheses
We present explainable artificial intelligence (XAI) models fit on a large longitudinal dataset that can predict perceptual thresholds on individual Argus II electrodes over time.
Galen Pogoncheff, Zuying Hu, Ariel Rokem, Michael Beyeler medRxiv:23285633
