Saved in:
Bibliographic Details
Main Authors: Dobek, Kacper, Jankowski, Daniel, Krawiec, Krzysztof
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18014
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909917554671616
author Dobek, Kacper
Jankowski, Daniel
Krawiec, Krzysztof
author_facet Dobek, Kacper
Jankowski, Daniel
Krawiec, Krzysztof
contents This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across three datasets. Compared to a convolutional baseline and an LSTM, both architectures achieved lower MAE, faster convergence, smaller model sizes, and favorable query times, though with slightly lower Pearson correlation. Their efficiency and adaptability make them well suited for scenarios with limited data and frequent retraining, such as edge deployments in vision prosthetics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18014
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling Retinal Ganglion Cells with Neural Differential Equations
Dobek, Kacper
Jankowski, Daniel
Krawiec, Krzysztof
Computer Vision and Pattern Recognition
Artificial Intelligence
This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across three datasets. Compared to a convolutional baseline and an LSTM, both architectures achieved lower MAE, faster convergence, smaller model sizes, and favorable query times, though with slightly lower Pearson correlation. Their efficiency and adaptability make them well suited for scenarios with limited data and frequent retraining, such as edge deployments in vision prosthetics.
title Modeling Retinal Ganglion Cells with Neural Differential Equations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.18014