Continual Learning on the Edge with TensorFlow Lite
- URL: http://arxiv.org/abs/2105.01946v1
- Date: Wed, 5 May 2021 09:32:06 GMT
- Title: Continual Learning on the Edge with TensorFlow Lite
- Authors: Giorgos Demosthenous and Vassilis Vassiliades
- Abstract summary: We show that transfer learning suffers from catastrophic forgetting when faced with more realistic scenarios.
We also open-source the code of our Android application to enable developers to integrate continual learning to their own smartphone applications.
- Score: 0.76146285961466
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deploying sophisticated deep learning models on embedded devices with the
purpose of solving real-world problems is a struggle using today's technology.
Privacy and data limitations, network connection issues, and the need for fast
model adaptation are some of the challenges that constitute today's approaches
unfit for many applications on the edge and make real-time on-device training a
necessity. Google is currently working on tackling these challenges by
embedding an experimental transfer learning API to their TensorFlow Lite,
machine learning library. In this paper, we show that although transfer
learning is a good first step for on-device model training, it suffers from
catastrophic forgetting when faced with more realistic scenarios. We present
this issue by testing a simple transfer learning model on the CORe50 benchmark
as well as by demonstrating its limitations directly on an Android application
we developed. In addition, we expand the TensorFlow Lite library to include
continual learning capabilities, by integrating a simple replay approach into
the head of the current transfer learning model. We test our continual learning
model on the CORe50 benchmark to show that it tackles catastrophic forgetting,
and we demonstrate its ability to continually learn, even under non-ideal
conditions, using the application we developed. Finally, we open-source the
code of our Android application to enable developers to integrate continual
learning to their own smartphone applications, as well as to facilitate further
development of continual learning functionality into the TensorFlow Lite
environment.
Related papers
- PIVOT: Prompting for Video Continual Learning [50.80141083993668]
We introduce PIVOT, a novel method that leverages extensive knowledge in pre-trained models from the image domain.
Our experiments show that PIVOT improves state-of-the-art methods by a significant 27% on the 20-task ActivityNet setup.
arXiv Detail & Related papers (2022-12-09T13:22:27Z) - 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) - Continual-Learning-as-a-Service (CLaaS): On-Demand Efficient Adaptation
of Predictive Models [17.83007940710455]
Two main future trends for companies that want to build machine learning-based applications are real-time inference and continual updating.
This paper defines a novel software service and model delivery infrastructure termed Continual Learning-as-a-Service (CL) to address these issues.
It provides support for model updating and validation tools for data scientists without an on-premise solution and in an efficient, stateful and easy-to-use manner.
arXiv Detail & Related papers (2022-06-14T16:22:54Z) - Learning Rate Curriculum [75.98230528486401]
We propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC)
LeRaC uses a different learning rate for each layer of a neural network to create a data-agnostic curriculum during the initial training epochs.
We compare our approach with Curriculum by Smoothing (CBS), a state-of-the-art data-agnostic curriculum learning approach.
arXiv Detail & Related papers (2022-05-18T18:57:36Z) - Online Continual Learning for Embedded Devices [41.31925039882364]
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.
arXiv Detail & Related papers (2022-03-21T00:23:09Z) - SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines.
This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
arXiv Detail & Related papers (2021-12-22T14:45:37Z) - Active Learning for Deep Neural Networks on Edge Devices [0.0]
This paper formalizes a practical active learning problem for neural networks on edge devices.
We propose a general task-agnostic framework to tackle this problem, which reduces it to a stream submodular property.
We evaluate our approach on both classification and object detection tasks in a practical setting to simulate a real-life scenario.
arXiv Detail & Related papers (2021-06-21T03:55:33Z) - 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) - Robustness of on-device Models: Adversarial Attack to Deep Learning
Models on Android Apps [14.821745719407037]
Most deep learning models within Android apps can easily be obtained via mature reverse engineering.
In this study, we propose a simple but effective approach to hacking deep learning models using adversarial attacks.
arXiv Detail & Related papers (2021-01-12T10:49:30Z) - Federated and continual learning for classification tasks in a society
of devices [59.45414406974091]
Light Federated and Continual Consensus (LFedCon2) is a new federated and continual architecture that uses light, traditional learners.
Our method allows powerless devices (such as smartphones or robots) to learn in real time, locally, continuously, autonomously and from users.
In order to test our proposal, we have applied it in a heterogeneous community of smartphone users to solve the problem of walking recognition.
arXiv Detail & Related papers (2020-06-12T12:37:03Z) - Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G
Networks [84.2155885234293]
We first summarize how to apply data-driven supervised deep learning and deep reinforcement learning in URLLC.
To address these open problems, we develop a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC.
arXiv Detail & Related papers (2020-02-22T14:38:11Z)
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.