Online Continual Learning for Embedded Devices

• URL: http://arxiv.org/abs/2203.10681v1
• Date: Mon, 21 Mar 2022 00:23:09 GMT
• Title: Online Continual Learning for Embedded Devices
• Authors: Tyler L. Hayes, Christopher Kanan
• Abstract summary: Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets. embedded devices have limited memory and compute capacity. Online continual learning models have been developed, but their effectiveness for embedded applications has not been rigorously studied.
• Score: 41.31925039882364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets. However, this setting poses unique challenges: embedded devices have limited memory and compute capacity and conventional machine learning models suffer from catastrophic forgetting when updated on non-stationary data streams. While several online continual learning models have been developed, their effectiveness for embedded applications has not been rigorously studied. In this paper, we first identify criteria that online continual learners must meet to effectively perform real-time, on-device learning. We then study the efficacy of several online continual learning methods when used with mobile neural networks. We measure their performance, memory usage, compute requirements, and ability to generalize to out-of-domain inputs.

Related papers

• Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices [26.939025828011196]
  The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. We propose a Constraint-aware Adaptive Exact Unlearning System at the network Edge (CAUSE) to enable exact unlearning on resource-constrained devices.
  arXiv  Detail & Related papers  (2024-10-14T03:28:09Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [49.043599241803825]
  Iterative Contrastive Unlearning (ICU) framework consists of three core components. A Knowledge Unlearning Induction module removes specific knowledge through an unlearning loss. A Contrastive Learning Enhancement module to preserve the model's expressive capabilities against the pure unlearning goal. And an Iterative Unlearning Refinement module that dynamically assess the unlearning extent on specific data pieces and make iterative update.
  arXiv  Detail & Related papers  (2024-07-25T07:09:35Z)
• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• PILOT: A Pre-Trained Model-Based Continual Learning Toolbox [71.63186089279218]
  This paper introduces a pre-trained model-based continual learning toolbox known as PILOT. On the one hand, PILOT implements some state-of-the-art class-incremental learning algorithms based on pre-trained models, such as L2P, DualPrompt, and CODA-Prompt. On the other hand, PILOT fits typical class-incremental learning algorithms within the context of pre-trained models to evaluate their effectiveness.
  arXiv  Detail & Related papers  (2023-09-13T17:55:11Z)
• Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors [68.8204255655161]
  This paper compares four state-of-the-art algorithms in two real applications: gesture recognition based on accelerometer data and image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs.
  arXiv  Detail & Related papers  (2022-09-01T17:05:20Z)
• Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks [0.0]
  Continual learning, also known as lifelong learning, is an emerging research topic that has been attracting increasing interest in the field of machine learning. We build on recent advances in the area of continual machine learning and design a lifelong adaptive learning framework using Prototypical Networks, LAPNet-HAR. LAPNet-HAR processes sensor-based data streams in a task-free data-incremental fashion and mitigates catastrophic forgetting using experience replay and continual prototype adaptation.
  arXiv  Detail & Related papers  (2022-03-11T00:57:29Z)
• Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications [19.334890205028568]
  We conduct the first comprehensive empirical study that quantifies the performance of three predominant continual learning schemes. We implement an end-to-end continual learning framework on edge devices. We demonstrate for the first time that it is feasible and practical to run continual learning on-device with a limited memory budget.
  arXiv  Detail & Related papers  (2021-10-25T22:06:26Z)
• Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data [101.6195176510611]
  "Online" continual learning enables evaluating both information retention and online learning efficacy. In online continual learning, each incoming small batch of data is first used for testing and then added to the training set, making the problem truly online. We introduce a new benchmark for online continual visual learning that exhibits large scale and natural distribution shifts.
  arXiv  Detail & Related papers  (2021-08-20T06:17:20Z)
• Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks [15.276951055528237]
  We review the state-of-the-art methods that allow continuous learning of computational models over time. We focus on the learning algorithms that perform continuous learning in an online fashion from considerably large (or infinite) sequential data. We critically analyze the key challenges associated with continual learning for autonomous real-world systems.
  arXiv  Detail & Related papers  (2021-05-26T07:38:20Z)
• Continual Learning at the Edge: Real-Time Training on Smartphone Devices [11.250227901473952]
  This paper describes the implementation and deployment of a hybrid learning strategy (AR1*) on a native Android application for real-time on-device personalization without forgetting. Our benchmark, based on an extension of the CORe50 dataset, shows the efficiency and effectiveness of our solution.
  arXiv  Detail & Related papers  (2021-05-24T12:00:31Z)

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.