Eva Dyer
University of Pennsylvania, PA·Computer Science·Early-career
Reaching for a glass, hearing leaves rustle or playing chess all rely on large circuits of neurons spread across the brain. New recording tools can measure hundreds or thousands of neurons at once.
- Fields
Computer Science
Neuroscience
Biomedical Engineering
- Topics
computational neuroscience
machine learning
neural population activity
- Grants
- 1 known grant, through Dec 2027
What they work on
- Develop self-supervised and contrastive learning methods that learn representations of neural population activity that stay stable despite irrelevant variation.
- Learn representations jointly across multiple neural recordings to identify the factors shared across individuals and the ways individuals differ.
- Extract dynamic latent factors that capture how neural representations shift over long time scales, and apply them to study healthy aging and neurodegenerative disease.
More about the research
However, reading intent or behavior out of these recordings is still hard. Recordings also differ from person to person and drift over time. This project develops machine learning methods that reliably link neural activity to complex behavior.
Why it matters
Better tools for decoding behavior from large neural recordings could help neuroscientists understand how the brain computes. The methods could also let researchers compare brains across individuals and track how brain activity changes with healthy aging and neurodegenerative disease.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Noah Snavely
Cornell University, NY·Computer Science
Develop compositional implicit neural scene representations that pair a network's ability to capture fine detail with physical models of scene structure, such as light fields.
Carl Vondrick
Columbia University, NY·Computer Science·Early-career
Build open-world recognition models for satellite, aerial and ground imagery from vision-language models without language annotations, using cross-modal contrastive learning and reasoning about change over time.
Philip Yu
University of Illinois Chicago, IL·Computer Science
Integrate open-source anomaly detection tools for tabular, graph and time-series data into a single OpenAD ecosystem with a standardized development environment for building and evaluating models.
The school
University of Pennsylvania: 90 labs on PI Pages, $2.2B a year on research, 750 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.