paper-with-me

Papers

LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms

2023-11-19 · Young D. Kwon, Jagmohan Chauhan, Hong Jia, Stylianos I. Venieris, Cecilia Mascolo

Continual Learning (CL) allows applications such as user personalization and household robots to learn on the fly and adapt to context. This is an important feature when context, actions, and users change. However, enabling CL on resource-constrained embedded systems is challenging due to the limited labeled data, memory, and computing capacity. In this paper, we propose LifeLearner, a hardware-aware meta continual learning system that drastically optimizes system resources (lower memory, latency, energy consumption) while ensuring high accuracy. Specifically, we (1) exploit meta-learning and rehearsal strategies to explicitly cope with data scarcity issues and ensure high accuracy, (2) effectively combine lossless and lossy compression to significantly reduce the resource requirements of CL and rehearsal samples, and (3) developed hardware-aware system on embedded and IoT platforms considering the hardware characteristics. As a result, LifeLearner achieves near-optimal CL performance, falling short by only 2.8% on accuracy compared to an Oracle baseline. With respect to the state-of-the-art (SOTA) Meta CL method, LifeLearner drastically reduces the memory footprint (by 178.7x), end-to-end latency by 80.8-94.2%, and energy consumption by 80.9-94.2%. In addition, we successfully deployed LifeLearner on two edge devices and a microcontroller unit, thereby enabling efficient CL on resource-constrained platforms where it would be impractical to run SOTA methods and the far-reaching deployment of adaptable CL in a ubiquitous manner. Code is available at https://github.com/theyoungkwon/LifeLearner.

📄 PDF Abstract BibTeX arXiv:2311.11420

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningMeta-Learning

Similar Papers 제목 키워드 기반

Improving Meta-Continual Learning Representations with Representation Replay

2021-09-29 · Lawrence Ki-On Chan, James Kwok

Continual learning often suffers from catastrophic forgetting. Recently, meta-continual learning algorithms use meta-learning to learn how to continually learn. A recent state-of-the-art is online aware meta-learning (OM…

Continual LearningMeta-Learning

Toward Universal Medical Image Registration via Sharpness-Aware Meta-Continual Learning

2024-06-25 · Bomin Wang, Xinzhe Luo, Xiahai Zhuang

Current deep learning approaches in medical image registration usually face the challenges of distribution shift and data collection, hindering real-world deployment. In contrast, universal medical image registration aim…

Continual LearningImage RegistrationMedical Image RegistrationMeta-Learning

Meta-Learning for Natural Language Understanding under Continual Learning Framework

2020-11-03 · Jiacheng Wang, Yong Fan, Duo Jiang, Shiqing Li

Neural network has been recognized with its accomplishments on tackling various natural language understanding (NLU) tasks. Methods have been developed to train a robust model to handle multiple tasks to gain a general r…

Continual LearningMeta-LearningNatural Language Understanding

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search

2026-05-03 · Matteo Gambella, Fabrizio Pittorino, Manuel Roveri arxiv

Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transitions from static benchmarks to real-worl…

Neural Architecture SearchContinual Learning

ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing

2026-04-23 · Jebacyril Arockiaraj, Dhruv Parikh, Viktor Prasanna arxiv

On-device continual learning (CL) is critical for edge AI systems operating on non-stationary data streams, but most existing methods rely on backpropagation or exemplar-heavy classifiers, incurring substantial compute, …

Continual Learning