Machine Learning for Microcontroller-Class Hardware -- A Review
- URL: http://arxiv.org/abs/2205.14550v1
- Date: Sun, 29 May 2022 00:59:38 GMT
- Title: Machine Learning for Microcontroller-Class Hardware -- A Review
- Authors: Swapnil Sayan Saha, Sandeep Singh Sandha, Mani Srivastava
- Abstract summary: This paper highlights the unique challenges of enabling onboard machine learning for microcontroller class devices.
We introduce a closed-loop widely applicable workflow of machine learning model development for microcontroller class devices.
- Score: 1.5311932971314297
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The advancements in machine learning opened a new opportunity to bring
intelligence to the low-end Internet-of-Things nodes such as microcontrollers.
Conventional machine learning deployment has high memory and compute footprint
hindering their direct deployment on ultra resource-constrained microcontroller
nodes. This paper highlights the unique challenges of enabling onboard machine
learning for microcontroller class devices. Recently, researchers have used a
specialized model development cycle for resource-limited applications to ensure
the compute and latency budget is within the limits while still maintaining the
desired accuracy. We introduce a closed-loop widely applicable workflow of
machine learning model development for microcontroller class devices and show
that several classes of applications adopt a specific instance of it. We
present both qualitative and numerical insights into different stages of model
development by showcasing several applications. Finally, we identify the open
research challenges and unsolved questions demanding careful considerations
moving forward.
Related papers
- On-Device Language Models: A Comprehensive Review [26.759861320845467]
Review examines the challenges of deploying computationally expensive large language models on resource-constrained devices.
Paper investigates on-device language models, their efficient architectures, as well as state-of-the-art compression techniques.
Case studies of on-device language models from major mobile manufacturers demonstrate real-world applications and potential benefits.
arXiv Detail & Related papers (2024-08-26T03:33:36Z) - Machine Learning with Requirements: a Manifesto [114.97965827971132]
We argue that requirements definition and satisfaction can go a long way to make machine learning models even more fitting to the real world.
We show how the requirements specification can be fruitfully integrated into the standard machine learning development pipeline.
arXiv Detail & Related papers (2023-04-07T14:47:13Z) - Learnware: Small Models Do Big [69.88234743773113]
The prevailing big model paradigm, which has achieved impressive results in natural language processing and computer vision applications, has not yet addressed those issues, whereas becoming a serious source of carbon emissions.
This article offers an overview of the learnware paradigm, which attempts to enable users not need to build machine learning models from scratch, with the hope of reusing small models to do things even beyond their original purposes.
arXiv Detail & Related papers (2022-10-07T15:55:52Z) - Design Automation for Fast, Lightweight, and Effective Deep Learning
Models: A Survey [53.258091735278875]
This survey covers studies of design automation techniques for deep learning models targeting edge computing.
It offers an overview and comparison of key metrics that are used commonly to quantify the proficiency of models in terms of effectiveness, lightness, and computational costs.
The survey proceeds to cover three categories of the state-of-the-art of deep model design automation techniques.
arXiv Detail & Related papers (2022-08-22T12:12:43Z) - Automating In-Network Machine Learning [2.857025628729502]
Planter is an open-source framework for mapping trained machine learning models to programmable devices.
We show that Planter-based in-network machine learning algorithms can run at line rate, have a negligible effect on latency, coexist with standard switching functionality, and have no or minor accuracy trade-offs.
arXiv Detail & Related papers (2022-05-18T09:42:22Z) - Flashlight: Enabling Innovation in Tools for Machine Learning [50.63188263773778]
We introduce Flashlight, an open-source library built to spur innovation in machine learning tools and systems.
We see Flashlight as a tool enabling research that can benefit widely used libraries downstream and bring machine learning and systems researchers closer together.
arXiv Detail & Related papers (2022-01-29T01:03:29Z) - Frugal Machine Learning [7.460473725109103]
This paper investigates frugal learning, aimed to build the most accurate possible models using the least amount of resources.
The most promising algorithms are then assessed in a real-world scenario by implementing them in a smartwatch and letting them learn activity recognition models on the watch itself.
arXiv Detail & Related papers (2021-11-05T21:27:55Z) - From Machine Learning to Robotics: Challenges and Opportunities for
Embodied Intelligence [113.06484656032978]
Article argues that embodied intelligence is a key driver for the advancement of machine learning technology.
We highlight challenges and opportunities specific to embodied intelligence.
We propose research directions which may significantly advance the state-of-the-art in robot learning.
arXiv Detail & Related papers (2021-10-28T16:04:01Z) - Real-time Neural Networks Implementation Proposal for Microcontrollers [0.0]
This paper aims to show an implementation strategy of a Multilayer Perceptron (MLP) type neural network, in a low-cost, low-power platform.
A modular matrix-based microcontroller with the full classification process was implemented, and also the backpropagation training in the microcontroller.
The testing and validation were performed through Hardware in the Loop (HIL) of the Mean Squared Error (MSE) of the training process, classification result, and the processing time of each implementation module.
arXiv Detail & Related papers (2020-06-08T03:51:14Z) - Towards CRISP-ML(Q): A Machine Learning Process Model with Quality
Assurance Methodology [53.063411515511056]
We propose a process model for the development of machine learning applications.
The first phase combines business and data understanding as data availability oftentimes affects the feasibility of the project.
The sixth phase covers state-of-the-art approaches for monitoring and maintenance of a machine learning applications.
arXiv Detail & Related papers (2020-03-11T08:25:49Z)
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.