Abstract
We present a new data-driven approach to inferring spikes from calcium imaging signals using supervised training of non-linear spiking neuron models. Our technique yields a substantially better performance compared to previous generative modeling approaches, reconstructing spike trains accurately at high temporal resolution even from previously unseen datasets. Future data acquired in new experimental conditions can easily be used to further improve its spike prediction accuracy and generalization performance.
Copyright
The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC 4.0 International license.