cs.ARNov 18, 2026

Hypnos: A Dual-Phase End-to-End Platform for Scalable Continual Learning at the Edge

Authors: Guilherme Guedes, Marco Apolinario Lainez, Charlotte Frenkel

Organizations: Department of Microelectronics, Delft University of Technology, 2628 CD Delft, The Netherlands

Abstract

Continual learning (CL) enables neural networks to adapt to non-stationary data streams by mitigating catastrophic forgetting, offering a path to robust, private, and adaptable edge devices. Yet, porting CL to real-world edge devices remains challenging for two reasons: (i) online operation, where sensor data arrives one sample at a time and the device must adapt on-the-fly, and (ii) the low footprint of edge devices, which makes traditional error backpropagation training prohibitive. Inspired by the brain's wake and sleep cycles, the former for rapid adaptation with minimal resources and the latter for long-term consolidation, we introduce Hypnos, an open-source dual-phase platform for efficient CL at the edge. In the wake phase (e.g., daily operation), Hypnos relies on a low-footprint system-on-chip with a RISC-V microcontroller unit (MCU) targeting efficient inference and supporting lightweight gradient-free prototype updates. In the sleep phase (e.g., night-time charging), where wall-plug energy and larger memory budgets are available, a smart charger performs rehearsal-based gradient updates for consolidation. Deployed on a ZCU104 field-programmable gate array (FPGA) and synthesized in a 28-nm process, Hypnos is benchmarked on the CORe50 NICv2-391 protocol. It sets a new state-of-the-art accuracy of 78.6%-81.6% for edge CL systems, with an on-device latency of 7.79s-10.54s per sample depending on activation precision, and requires 3.8×3.8\times fewer learning steps and 22×22\times less learning compute than quantized latent replay at higher accuracy and comparable latency.

Figures & tables

Explore similar work

CardsList
  1. Leveraging ECRAM for Edge Continual Learning

    Jul 22, 2026Nabila Tasnim, Haoran Liu, Qing Cao +1Compute-in-MemoryContinual Learning

  2. Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge

    Apr 8, 2026Wonseon Lim, Jaesung Lee, Dae-Won KimPrompt-Based Continual LearningContinual Learning

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

    Nov 3, 2025Elvin Hajizada, Danielle Rager, Timothy Shea +5Online Continual LearningIncremental Learning