mlsanityData to 14 Oct 2026

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

arXiv 2511.01553 ↗First posted 3 Nov 2025cs.LG cs.AI cs.DCcited by 0

Not on the map. Why?

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.

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

28 of 55 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  4. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  5. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
  6. 2021Towards Open World Object Detectioncited by 297
  7. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  8. 2022On-Device Training Under 256KB Memorycited by 160
  9. 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 152
  10. 2021Efficient Neuromorphic Signal Processing with Loihi 2cited by 96
  11. 2021Rehearsal revealed: The limits and merits of revisiting samples in continual learningcited by 76
  12. 2021TinyOL: TinyML with Online-Learning on Microcontrollerscited by 65
16 more
  1. 2021Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworkscited by 56
  2. 2023On the Stability-Plasticity Dilemma of Class-Incremental Learningcited by 56
  3. 2022Online Continual Learning for Embedded Devicescited by 49
  4. 2023Efficient Video and Audio processing with Loihi 2cited by 29
  5. 2019OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learningcited by 28
  6. 2020Wandering Within a World: Online Contextualized Few-Shot Learningcited by 22
  7. 2021Continual Learning at the Edge: Real-Time Training on Smartphone Devicescited by 20
  8. 2019Rapid online learning and robust recall in a neuromorphic olfactory circuitcited by 18
  9. 2020Online Few-shot Gesture Learning on a Neuromorphic Processorcited by 18
  10. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  11. 2023Neurogenesis Dynamics-inspired Spiking Neural Network Training Accelerationcited by 10
  12. 2019Training on the Edge: The why and the howcited by 9
  13. 2025Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarkscited by 7
  14. 2020A Review of Open-World Learning and Steps Toward Open-World Learning Without Labelscited by 6
  15. 2024Continual Learning for Autonomous Robots: A Prototype-based Approachcited by 5
  16. 2023Efficient Rehearsal Free Zero Forgetting Continual Learning using Adaptive Weight Modulationcited by 1

Built on by

Not cited yet.