Timezone: »

 
Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings
Sabera Talukder · Jennifer J Sun · Matthew Leonard · Bingni Brunton · Yisong Yue

Fri Dec 02 09:30 AM -- 10:30 AM (PST) @
in Learning from Time Series for Health »
Event URL: https://openreview.net/forum?id=c9qFg8UrIcn »

We study the problem of time series imputation in multivariate neural recordings. Compared to standard time series imputation settings, new challenges for imputing neural recordings include the lack of adjacent timestamps for electrodes missing over days, and generalization across days and participants with different electrode configurations. Due to these challenges, the standard practice in neuroscience is to discard electrodes with missing data, even if only a part of the recording is corrupted, significantly reducing the already limited and difficult-to-obtain data. In this paper, we establish Deep Neural Imputation (DNI), a framework to recover missing electrode recordings by learning across sessions, spatial locations, and participants. We first instantiate DNI with natural linear baselines, then develop encoder-decoder approaches based on masked electrode modeling. We evaluate DNI on 12 multielectrode, human neural datasets with naturalistic behavior. We demonstrate DNI's data imputation ability across a broad range of metrics as well as integrate DNI into an existing neural data analysis pipeline.

Author Information

Sabera Talukder (Caltech)

Sabera Talukder is currently a PhD student at Caltech where she works on neuroengineering projects linking machine learning to human neural recordings. Previously, she worked as a software engineer at the Chan Zuckerberg Biohub where she lead the neuroengineering initiative. She attended Stanford University for undergrad and double majored with honors in both electrical engineering and biology. Visit her personal page to learn more: https://saberatalukder.com/

Jennifer J Sun (Caltech)
Matthew Leonard (University of California, San Francisco)
Bingni Brunton (University of Washington)
Yisong Yue (Caltech)

More from the Same Authors