arXiv cs.AI· Elvin Hajizada, Danielle Rager, Timothy Shea, Leobardo Campos-Macias, Andreas Wild, Eyke H\"ullermeier, Yulia Sandamirskaya, Mike Davies·· 12 小时前AI 评分34
CLP-SNN：在 Intel Loihi 2 上实现在线持续学习的脉冲神经网络
Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
AI 导读
CLP-SNN 将 Continually Learning Prototypes 算法重构为事件驱动的脉冲神经网络动态，成为 Intel Loihi 2 上首个在线持续学习器。
正文 · 原文
Abstract:Edge AI must adapt to new classes and shifting data within a tight power budget, but online continual learning (learning from each sample before the next arrives) is where conventional processors are least efficient: each small update pays a full dispatch at full power. We present CLP-SNN, a spiking architecture that recasts the Continually Learning Prototypes (CLP) algorithm as event-driven neural dynamics: a self-normalizing local rule replaces CLP's global renormalization, prototype allocation becomes novelty-triggered neurogenesis, and correctness-modulated plasticity becomes reward-gated per-neuron metaplasticity. Deployed on Intel Loihi 2 as the first online continual learner on that chip, rehearsal-free CLP-SNN matches Replay and SLDA on OpenLORIS at 1-shot; at 25-shot, it stays within 0.8 percentage points of Replay and 6.2 points below covariance-based SLDA. Each prediction-and-update step on extracted features completes on-chip in 0.33 ms at 0.05 mJ, 7.3x lower latency and 341x lower energy than Replay on a Jetson Orin Nano.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Neural and Evolutionary Computing (cs.NE) |
| Cite as: | arXiv:2511.01553 [cs.LG] |
| (or arXiv:2511.01553v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2511.01553 arXiv-issued DOI via DataCite |
Submission history
From: Elvin Hajizada [view email]
[v1]
Mon, 3 Nov 2025 13:16:16 UTC (517 KB)
[v2]
Tue, 5 May 2026 20:15:29 UTC (777 KB)
[v3]
Tue, 20 Oct 2026 08:41:18 UTC (781 KB)
来源：arXiv cs.AI · arxiv.org