ePoster

CONDUCTANCE-BASED REVERSAL POTENTIALS IN SPIKING RECURRENT NEURAL NETWORKS ENHANCE ENERGY EFFICIENCY AND TASK PERFORMANCE

Miguel Rodriguesand 2 co-authors

Radboud University

FENS Forum 2026 (2026)
Barcelona, Spain
Board PS05-09AM-663

Presentation

Date TBA

Board: PS05-09AM-663

Poster preview

CONDUCTANCE-BASED REVERSAL POTENTIALS IN SPIKING RECURRENT NEURAL NETWORKS ENHANCE ENERGY EFFICIENCY AND TASK PERFORMANCE poster preview

Event Information

Poster Board

PS05-09AM-663

Abstract

Spiking recurrent neural networks (SRNNs) rival gated RNNs on various tasks, yet they still lack several hallmarks of biological neural networks. We introduce a biologically grounded SRNN that implements Dale’s law with AMPA and GABA voltage reversal potentials. These reversal potentials modulate synaptic gain as a function of the postsynaptic membrane potential, and we derive theoretically how they make each neuron’s effective dynamics and subthreshold resonance input-dependent. We trained SRNNs on the Spiking Heidelberg Digits dataset, and show that SRNN with reversal potentials cuts spike energy by up to 4×, while increasing task accuracy. This leads to high-performing Dalean SRNNs, substantially improving on Dalean networks without reversal potentials. Thus, Dale’s law with reversal potentials, a core feature of biological neural networks, can render SRNNs more accurate and energy-efficient.

Recommended posters

Cookies

We use essential cookies to run the site. Analytics cookies are optional and help us improve World Wide. Learn more.