LGAIDCNENov 3, 2025

Real-time Continual Learning on Intel Loihi 2

arXiv:2511.01553v11 citationsh-index: 69
Originality Highly original
AI Analysis

This work addresses the problem of adapting AI systems to shifting data distributions in power-constrained edge environments, offering a transformative solution with significant efficiency gains.

The paper tackles the challenge of online continual learning on edge devices by proposing CLP-SNN, a neuromorphic spiking neural network implemented on Intel Loihi 2, achieving competitive accuracy on OpenLORIS while being 70× faster and 5,600× more energy efficient than edge GPU alternatives.

AI systems on edge devices face a critical challenge in open-world environments: adapting when data distributions shift and novel classes emerge. While offline training dominates current paradigms, online continual learning (OCL)--where models learn incrementally from non-stationary streams without catastrophic forgetting--remains challenging in power-constrained settings. We present a neuromorphic solution called CLP-SNN: a spiking neural network architecture for Continually Learning Prototypes and its implementation on Intel's Loihi 2 chip. Our approach introduces three innovations: (1) event-driven and spatiotemporally sparse local learning, (2) a self-normalizing three-factor learning rule maintaining weight normalization, and (3) integrated neurogenesis and metaplasticity for capacity expansion and forgetting mitigation. On OpenLORIS few-shot learning experiments, CLP-SNN achieves accuracy competitive with replay methods while being rehearsal-free. CLP-SNN delivers transformative efficiency gains: 70\times faster (0.33ms vs 23.2ms), and 5,600\times more energy efficient (0.05mJ vs 281mJ) than the best alternative OCL on edge GPU. This demonstrates that co-designed brain-inspired algorithms and neuromorphic hardware can break traditional accuracy-efficiency trade-offs for future edge AI systems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes