# Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network

arXiv: https://arxiv.org/abs/2511.01553 · HTML: https://mlsanity.com/paper/2511.01553/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Challenges in Deploying Machine Learning: a Survey of Case Studies](https://mlsanity.com/paper/2011.09926/) (2020)
- [Efficient Neuromorphic Signal Processing with Loihi 2](https://mlsanity.com/paper/2111.03746/) (2021)
- [Rehearsal revealed: The limits and merits of revisiting samples in continual learning](https://mlsanity.com/paper/2104.07446/) (2021)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks](https://mlsanity.com/paper/2105.12374/) (2021)
- [On the Stability-Plasticity Dilemma of Class-Incremental Learning](https://mlsanity.com/paper/2304.01663/) (2023)
- [Online Continual Learning for Embedded Devices](https://mlsanity.com/paper/2203.10681/) (2022)
- [Efficient Video and Audio processing with Loihi 2](https://mlsanity.com/paper/2310.03251/) (2023)
- [OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning](https://mlsanity.com/paper/1911.06487/) (2019)
- [Wandering Within a World: Online Contextualized Few-Shot Learning](https://mlsanity.com/paper/2007.04546/) (2020)
- [Continual Learning at the Edge: Real-Time Training on Smartphone Devices](https://mlsanity.com/paper/2105.13127/) (2021)
- [Rapid online learning and robust recall in a neuromorphic olfactory circuit](https://mlsanity.com/paper/1906.07067/) (2019)
- [Online Few-shot Gesture Learning on a Neuromorphic Processor](https://mlsanity.com/paper/2008.01151/) (2020)
- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration](https://mlsanity.com/paper/2304.12214/) (2023)
- [Training on the Edge: The why and the how](https://mlsanity.com/paper/1903.03051/) (2019)
- [Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks](https://mlsanity.com/paper/2501.04897/) (2025)
- [A Review of Open-World Learning and Steps Toward Open-World Learning Without Labels](https://mlsanity.com/paper/2011.12906/) (2020)
- [Continual Learning for Autonomous Robots: A Prototype-based Approach](https://mlsanity.com/paper/2404.00418/) (2024)
- [Efficient Rehearsal Free Zero Forgetting Continual Learning using Adaptive Weight Modulation](https://mlsanity.com/paper/2311.15276/) (2023)

## Abstract (arXiv)

AI systems on edge devices require online continual learning -- adapting to non-stationary streams and unfamiliar classes without catastrophic forgetting -- under strict power constraints. We present CLP-SNN, a spiking neural network with a self-normalizing local learning rule and a spike-driven neural state machine for autonomous on-chip learning, implemented on Intel's Loihi 2 neuromorphic processor. On OpenLORIS few-shot experiments, CLP-SNN matches replay-based accuracy rehearsal-free. On Loihi 2, CLP-SNN achieves 113x lower latency (0.33 ms vs. 37.3 ms) and 6,600x lower energy (0.05 mJ vs. 333 mJ) than the strongest edge-GPU baseline. This gain decomposes into algorithmic efficiency (~14.5x latency, ~22.6x energy on the same GPU) and neuromorphic hardware co-design (~7.8x latency, ~295x energy) exploiting event-driven learning and sparse graded-spike communication. We show that co-designed brain-inspired algorithms and neuromorphic hardware can break traditional accuracy-efficiency trade-offs in edge AI.