Article
A dataset of differentiable biologically-derived single neuron models
2025-12-05
Abstract excerpt
Biological neural networks contain diverse cell types with heterogeneous electrophysiological properties. Artificial neural networks (ANNs) model computational aspects of biology but use homogeneous neurons, limiting realism. A key obstacle to building bio-inspired ANNs is the absence of a database of neuron models that both fit biological data and remain differentiable for gradient-based learning. We present such...
Topics
Open a Topic to create a Post that cites this publication.
Identifiers and source
- Literature Corpus work
- 76f85b3a-8d82-586c-b82d-4cb8eead2c06
- DOI
- 10.64898/2025.12.02.691895
