Spike Distance Function as a Learning Objective for Spike Prediction

Kevin Doran, Marvin Seifert, Carola A. M. Yovanovich, Tom Baden
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11474-11500, 2024.

Abstract

Approaches to predicting neuronal spike responses commonly use a Poisson learning objective. This objective quantizes responses into spike counts within a fixed summation interval, typically on the order of 10 to 100 milliseconds in duration; however, neuronal responses are often time accurate down to a few milliseconds, and Poisson models struggle to precisely model them at these timescales. We propose the concept of a spike distance function that maps points in time to the temporal distance to the nearest spike. We show that neural networks can be trained to approximate spike distance functions, and we present an efficient algorithm for inferring spike trains from the outputs of these models. Using recordings of chicken and frog retinal ganglion cells responding to visual stimuli, we compare the performance of our approach to that of Poisson models trained with various summation intervals. We show that our approach outperforms the use of Poisson models at spike train inference.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-doran24a, title = {Spike Distance Function as a Learning Objective for Spike Prediction}, author = {Doran, Kevin and Seifert, Marvin and Yovanovich, Carola A. M. and Baden, Tom}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {11474--11500}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/doran24a/doran24a.pdf}, url = {https://proceedings.mlr.press/v235/doran24a.html}, abstract = {Approaches to predicting neuronal spike responses commonly use a Poisson learning objective. This objective quantizes responses into spike counts within a fixed summation interval, typically on the order of 10 to 100 milliseconds in duration; however, neuronal responses are often time accurate down to a few milliseconds, and Poisson models struggle to precisely model them at these timescales. We propose the concept of a spike distance function that maps points in time to the temporal distance to the nearest spike. We show that neural networks can be trained to approximate spike distance functions, and we present an efficient algorithm for inferring spike trains from the outputs of these models. Using recordings of chicken and frog retinal ganglion cells responding to visual stimuli, we compare the performance of our approach to that of Poisson models trained with various summation intervals. We show that our approach outperforms the use of Poisson models at spike train inference.} }
Endnote
%0 Conference Paper %T Spike Distance Function as a Learning Objective for Spike Prediction %A Kevin Doran %A Marvin Seifert %A Carola A. M. Yovanovich %A Tom Baden %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-doran24a %I PMLR %P 11474--11500 %U https://proceedings.mlr.press/v235/doran24a.html %V 235 %X Approaches to predicting neuronal spike responses commonly use a Poisson learning objective. This objective quantizes responses into spike counts within a fixed summation interval, typically on the order of 10 to 100 milliseconds in duration; however, neuronal responses are often time accurate down to a few milliseconds, and Poisson models struggle to precisely model them at these timescales. We propose the concept of a spike distance function that maps points in time to the temporal distance to the nearest spike. We show that neural networks can be trained to approximate spike distance functions, and we present an efficient algorithm for inferring spike trains from the outputs of these models. Using recordings of chicken and frog retinal ganglion cells responding to visual stimuli, we compare the performance of our approach to that of Poisson models trained with various summation intervals. We show that our approach outperforms the use of Poisson models at spike train inference.
APA
Doran, K., Seifert, M., Yovanovich, C.A.M. & Baden, T.. (2024). Spike Distance Function as a Learning Objective for Spike Prediction. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:11474-11500 Available from https://proceedings.mlr.press/v235/doran24a.html.

Related Material