# Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?

arXiv: https://arxiv.org/abs/2401.08602 · HTML: https://mlsanity.com/paper/2401.08602/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 21 Nov 2023.

## Builds on (most cited first, 17 of 17)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [End-to-end Learning of Driving Models from Large-scale Video Datasets](https://mlsanity.com/paper/1612.01079/) (2016)
- [Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration](https://mlsanity.com/paper/2105.06411/) (2021)
- [VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles](https://mlsanity.com/paper/2111.12083/) (2021)
- [On Offline Evaluation of Vision-based Driving Models](https://mlsanity.com/paper/1809.04843/) (2018)
- [Minimal Gated Unit for Recurrent Neural Networks](https://mlsanity.com/paper/1603.09420/) (2016)
- [VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation](https://mlsanity.com/paper/2105.09371/) (2021)
- [Causal Navigation by Continuous-time Neural Networks](https://mlsanity.com/paper/2106.08314/) (2021)
- [VisualBackProp: efficient visualization of CNNs](https://mlsanity.com/paper/1611.05418/) (2016)
- [Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator](https://mlsanity.com/paper/2008.13193/) (2020)
- [Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap](https://mlsanity.com/paper/2210.04303/) (2022)
- [Real time implementation of CTRNN and BPTT algorithm to learn on-line biped robot balance: Experiments on the standing posture](https://mlsanity.com/paper/2011.06910/) (2020)

## Built on by (most cited first, 5 of 5)

- [Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling](https://mlsanity.com/paper/2505.21717/) (2025)
- [TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecasting](https://mlsanity.com/paper/2503.05108/) (2025)
- [Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents](https://mlsanity.com/paper/2503.16711/) (2025)
- [Adaptive Control in Autonomous Driving via Real-Time Recurrent RL](https://mlsanity.com/paper/2602.02236/) (2026)
- [Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models](https://mlsanity.com/paper/2602.13017/) (2026)

## Abstract (arXiv)

Bio-inspired neural networks have the potential to advance our understanding of neural computation and improve the state-of-the-art of AI systems. Bio-electrical synapses directly transmit neural signals, by enabling fast current flow between neurons. In contrast, bio-chemical synapses transmit neural signals indirectly, through neurotransmitters. Prior work showed that interpretable dynamics for complex robotic control, can be achieved by using chemical synapses, within a sparse, bio-inspired architecture, called Neural Circuit Policies (NCPs). However, a comparison of these two synaptic models, within the same architecture, remains an unexplored area. In this work we aim to determine the impact of using chemical synapses compared to electrical synapses, in both sparse and all-to-all connected networks. We conduct experiments with autonomous lane-keeping through a photorealistic autonomous driving simulator to evaluate their performance under diverse conditions and in the presence of noise. The experiments highlight the substantial influence of the architectural and synaptic-model choices, respectively. Our results show that employing chemical synapses yields noticeable improvements compared to electrical synapses, and that NCPs lead to better results in both synaptic models.