Real-time Continual Learning on Intel Loihi 2

• URL: http://arxiv.org/abs/2511.01553v1
• Date: Mon, 03 Nov 2025 13:16:16 GMT
• Title: Real-time Continual Learning on Intel Loihi 2
• Abstract summary: We present a neuromorphic solution called CLP-SNN for online continual learning.<n>CLP-SNN delivers transformative efficiency gains.<n>This demonstrates that co-designed brain-inspired algorithms and neuromorphic hardware can break traditional accuracy-efficiency trade-offs for future edge AI systems.
• Score: 22.180269101937565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras [28.615063153642144]
  We present CLANE, Continual Learning of Actions on Neuromorphic Hardware from Event Cameras, deployed end-to-end on Intel Loihi 2.<n>We achieve 70.4% accuracy in a continual learning task while delivering more than 100x energy reduction and 16x lower latency over a sequential CNN+GRU+CLP edge GPU baseline.
  arXiv  Detail & Related papers  (2026-05-27T12:24:04Z)
• The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks [0.0]
  Recent advancements in QML and SNNs have generated considerable excitement.<n>This paper argues that they are unlikely to displace DNNs in the near term.<n>DNNs leverage efficient backpropagation, robust regularization, and innovations in LRMs that shift scaling to inference-time compute.
  arXiv  Detail & Related papers  (2025-10-04T11:00:46Z)
• Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference [0.0]
  We present the first embedded FPGA accelerator for BCPNN on a Zynq UltraScale+ system using High-Level Synthesis.<n>Our accelerator achieves up to 17.5x latency and 94% energy savings over ARM baselines, without sacrificing accuracy.<n>This work enables practical neuromorphic computing on edge devices, bridging the gap between brain-like learning and real-world deployment.
  arXiv  Detail & Related papers  (2025-06-23T11:35:20Z)
• Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control [59.65431931190187]
  Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware.<n>Most continuous control algorithms for continuous control are designed for Artificial Neural Networks (ANNs)<n>We show that this mismatch destabilizes SNN training and degrades performance.<n>We propose a novel proxy target framework to bridge the gap between discrete SNNs and continuous-control algorithms.
  arXiv  Detail & Related papers  (2025-05-30T03:08:03Z)
• A Reconfigurable Stream-Based FPGA Accelerator for Bayesian Confidence Propagation Neural Networks [0.0]
  Brain-inspired algorithms are attractive and emerging alternatives to classical deep learning methods.<n>BCPNN is an important tool for both machine learning and computational neuroscience research.<n>BCPNN can reach state-of-the-art performance in tasks such as learning and memory recall compared to other models.<n>We design a custom stream-based accelerator for BCPNN using Field-Programmable Gate Arrays (FPGA) using Xilinx Vitis High-Level Synthesis (HLS) flow.
  arXiv  Detail & Related papers  (2025-03-03T14:06:43Z)
• Activation-wise Propagation: A Universal Strategy to Break Timestep Constraints in Spiking Neural Networks for 3D Data Processing [29.279985043923386]
  We introduce Activation-wise Membrane Potential Propagation (AMP2), a novel state update mechanism for spiking neurons.<n>Inspired by skip connections in deep networks, AMP2 incorporates the membrane potential of neurons into network, eliminating the need for iterative updates.<n>Our method achieves significant improvements across various 3D modalities, including 3D point clouds and event streams.
  arXiv  Detail & Related papers  (2025-02-18T11:52:25Z)
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks [56.35403810762512]
  Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. We study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method.
  arXiv  Detail & Related papers  (2023-02-01T04:22:59Z)
• ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware [105.54048699217668]
  We show a competitive performance in accuracy with a clear advantage in the computational complexity for Event-Based Three-factor Local Plasticity (ETLP) We also show that when using local plasticity, threshold adaptation in spiking neurons and a recurrent topology are necessary to learntemporal patterns with a rich temporal structure.
  arXiv  Detail & Related papers  (2023-01-19T19:45:42Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Training Spiking Neural Networks with Local Tandem Learning [96.32026780517097]
  Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient than their predecessors. In this paper, we put forward a generalized learning rule, termed Local Tandem Learning (LTL) We demonstrate rapid network convergence within five training epochs on the CIFAR-10 dataset while having low computational complexity.
  arXiv  Detail & Related papers  (2022-10-10T10:05:00Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization [10.005026783940682]
  Silicon-photonics-based optical neural network (ONN) is a promising hardware platform that could represent a paradigm shift in efficient AI. In this work, we propose a closed-loop ONN on-chip learning framework L2ight to enable scalable ONN mapping and efficient in-situ learning.
  arXiv  Detail & Related papers  (2021-10-27T22:53:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.