# TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents

arXiv: https://arxiv.org/abs/2303.01826 · HTML: https://mlsanity.com/paper/2303.01826/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## Placed in

- LLM agents and tool use / [Agentic AI for wireless networks](https://mlsanity.com/agents/agentic-ai-for-wireless-networks/)

## Builds on (most cited first, 14 of 14)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition](https://mlsanity.com/paper/1710.04734/) (2017)
- [BindsNET: A machine learning-oriented spiking neural networks library in Python](https://mlsanity.com/paper/1806.01423/) (2018)
- [Exploring the Connection Between Binary and Spiking Neural Networks](https://mlsanity.com/paper/2002.10064/) (2020)
- [FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2007.08860/) (2020)
- [SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments](https://mlsanity.com/paper/2103.00424/) (2021)
- [Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions](https://mlsanity.com/paper/2203.07006/) (2022)
- [SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAM](https://mlsanity.com/paper/2103.00421/) (2021)
- [ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories](https://mlsanity.com/paper/2108.10271/) (2021)
- [lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents](https://mlsanity.com/paper/2205.12295/) (2022)
- [One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency](https://mlsanity.com/paper/2110.05929/) (2021)
- [ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networks](https://mlsanity.com/paper/1703.07655/) (2017)
- [Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks](https://mlsanity.com/paper/1902.03187/) (2019)

## Built on by (most cited first, 14 of 14)

- [SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems](https://mlsanity.com/paper/2402.11322/) (2024)
- [QSViT: A Methodology for Quantizing Spiking Vision Transformers](https://mlsanity.com/paper/2504.00948/) (2025)
- [Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack](https://mlsanity.com/paper/2404.03325/) (2024)
- [RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults](https://mlsanity.com/paper/2304.04041/) (2023)
- [A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data](https://mlsanity.com/paper/2404.03493/) (2024)
- [SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents](https://mlsanity.com/paper/2404.09331/) (2024)
- [Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems](https://mlsanity.com/paper/2503.17061/) (2025)
- [QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models](https://mlsanity.com/paper/2601.00679/) (2026)
- [FastSpiker: Enabling Fast Training for Spiking Neural Networks on Event-based Data through Learning Rate Enhancements for Autonomous Embedded Systems](https://mlsanity.com/paper/2407.05262/) (2024)
- [Enabling Energy-Efficient Simultaneous Multi-Task Reinforcement Learning through Spiking Neural Networks with Active Dendrites for Bio-inspired Generalist Agents](https://mlsanity.com/paper/2412.04847/) (2024)
- [Real Time Scheduling Framework for Multi Object Detection via Spiking Neural Networks](https://mlsanity.com/paper/2501.18412/) (2025)
- [SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization](https://mlsanity.com/paper/2508.10913/) (2025)
- [SpikeVox: Towards Energy-Efficient Speech Therapy Framework with Spike-driven Generative Language Models](https://mlsanity.com/paper/2510.15566/) (2025)
- [PSViT: A Methodology for Structurally Pruning Spiking Vision Transformers](https://mlsanity.com/paper/2606.03257/) (2026)

## Abstract (arXiv)

Autonomous mobile agents require low-power/energy-efficient machine learning (ML) algorithms to complete their ML-based tasks while adapting to diverse environments, as mobile agents are usually powered by batteries. These requirements can be fulfilled by Spiking Neural Networks (SNNs) as they offer low power/energy processing due to their sparse computations and efficient online learning with bio-inspired learning mechanisms for adapting to different environments. Recent works studied that the energy consumption of SNNs can be optimized by reducing the computation time of each neuron for processing a sequence of spikes (timestep). However, state-of-the-art techniques rely on intensive design searches to determine fixed timestep settings for only inference, thereby hindering the SNNs from achieving further energy efficiency gains in both training and inference. These techniques also restrict the SNNs from performing efficient online learning at run time. Toward this, we propose TopSpark, a novel methodology that leverages adaptive timestep reduction to enable energy-efficient SNN processing in both training and inference, while keeping its accuracy close to the accuracy of SNNs without timestep reduction. The ideas of TopSpark include: analyzing the impact of different timesteps on the accuracy; identifying neuron parameters that have a significant impact on accuracy in different timesteps; employing parameter enhancements that make SNNs effectively perform learning and inference using less spiking activity; and developing a strategy to trade-off accuracy, latency, and energy to meet the design requirements. The results show that, TopSpark saves the SNN latency by 3.9x as well as energy consumption by 3.5x (training) and 3.3x (inference) on average, across different network sizes, learning rules, and workloads, while maintaining the accuracy within 2% of SNNs without timestep reduction.