RT Journal Article
SR Electronic
T1 Supervised learning sets benchmark for robust spike detection from calcium imaging signals
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 010777
DO 10.1101/010777
A1 Lucas Theis
A1 Philipp Berens
A1 Emmanouil Froudarakis
A1 Jacob Reimer
A1 Miroslav Román-Rosón
A1 Tom Baden
A1 Thomas Euler
A1 Andreas Tolias
A1 Matthias Bethge
YR 2014
UL http://biorxiv.org/content/early/2014/10/28/010777.abstract
AB 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.