Timezone: »

 
Using Sum-Product Networks to estimate neural population stutcture in the brain
Koosha Khalvati · Samantha Johnson · Stefan Mihalas · Michael Buice

@
in AI for Science: Progress and Promises »
Event URL: https://openreview.net/forum?id=bF1hSW-z_8 »

We present a computationally efficient framework to model a wide range of population structures with high order correlations and a large number of neurons. Our method is based on a special type of Bayesian network that has linear inference time and is founded upon the concept of contextual independence. Moreover, we use an efficient architecture learning method for network selection to model large neural populations even with a small amount of data. Our framework is both fast and accurate in approximating neural population structures. Furthermore, our approach enables us to reliably quantify higher order neural correlations. We test our method on publicly available large-scale neural recordings from the Allen Brain Observatory. Our approach significantly outperforms other models both in terms of statistical measures and alignment with experimental evidence.

Keywords: computational neuroscience · sum product networks · Probabilistic circuits

Author Information

Koosha Khalvati (University of Washington)
Samantha Johnson (University of Chicago)
Stefan Mihalas (Allen Institute for Brain Science)
Michael Buice (Allen Institute)

More from the Same Authors