# Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks

arXiv: https://arxiv.org/abs/2404.19419 · HTML: https://mlsanity.com/paper/2404.19419/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2024.

## Built on by (most cited first, 6 of 6)

- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems](https://mlsanity.com/paper/2503.17061/) (2025)
- [More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing](https://mlsanity.com/paper/2410.08003/) (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)
- [Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents](https://mlsanity.com/paper/2504.13541/) (2025)
- [CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras](https://mlsanity.com/paper/2605.28387/) (2026)

## Abstract (arXiv)

While the human brain efficiently adapts to new tasks from a continuous stream of information, neural network models struggle to learn from sequential information without catastrophically forgetting previously learned tasks. This limitation presents a significant hurdle in deploying edge devices in real-world scenarios where information is presented in an inherently sequential manner. Active dendrites of pyramidal neurons play an important role in the brain ability to learn new tasks incrementally. By exploiting key properties of time-to-first-spike encoding and leveraging its high sparsity, we present a novel spiking neural network model enhanced with active dendrites. Our model can efficiently mitigate catastrophic forgetting in temporally-encoded SNNs, which we demonstrate with an end-of-training accuracy across tasks of 88.3% on the test set using the Split MNIST dataset. Furthermore, we provide a novel digital hardware architecture that paves the way for real-world deployment in edge devices. Using a Xilinx Zynq-7020 SoC FPGA, we demonstrate a 100-% match with our quantized software model, achieving an average inference time of 37.3 ms and an 80.0% accuracy.