AS
Back to Work

Decoding Brain Activity at Scale

Team-led neuroscience pipelines and algorithms for massive calcium imaging datasets.

The problem

Harvard Medical School and FORTH needed to analyze communication patterns in neuronal activity.

The dataset scale was extreme: 10,000+ neurons generating 80GB+ of calcium imaging data.

What I built / changed

  • Led an 8-person data science team.
  • Built preprocessing pipelines and analysis tooling.
  • Developed ML algorithms for pattern detection.
  • Built visualization tools for researchers.
  • Applied statistical multivariate analysis and neural networks to extract insights.

Result

Published research on spontaneous brain activity patterns.

Stack / concepts

Big DataMLNeural networksResearch

Interested in discussing engineering challenges?

Get in touch