Widening Access to Applied Machine Learning with TinyML

Reddi, Vijay Janapa; Plancher, Brian; Kennedy, Susan; Moroney, Laurence; Warden, Pete; Suzuki, Lara; Agarwal, Anant; Banbury, Colby; Banzi, Massimo; Bennett, Matthew R.; Brown, Benjamin; Chitlangia, Sharad; Ghosal, Radhika; Grafman, Sarah; Jaeger, Rupert; Lam, Maximilian; Leiker, Daniel; Mann, Cara; Mazumder, Mark; Pajak, Dominic; Ramaprasad, Dhilan; Smith, John; Stewart, Matthew; Tingley, Dustin

doi:10.1162/99608f92.762d171a

Cited by 22 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks are usually trained on dedicated servers, while inference can be computed on the edge, even on very resource-constrained devices [46]. Recent developments are introducing continuous learning techniques [47], often employing custom-designed architectures [48]. TinyML systems are gaining more and more traction, and to support this expansion benchmarking [49][50] tools have been developed to assess ML performances at the edge.…”

Section: Related Workmentioning

confidence: 99%

Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring

Giordano¹,

Baumann²,

Crabolu

et al. 2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring

Giordano¹,

Baumann²,

Crabolu

et al. 2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

“…Moving a step forward, frameworks for characterizing and assessing ML deployment on the edge [20] [6] help us systematically tackle potential issues. Many platforms and resources, such as open online courses [22], X-CUBE-AI [29] from STM, Apache's TVM [4], and TensorFlow Lite for Microcontrollers [7] from Google, are made available to accelerate TinyML. Besides, remarkable applications of TinyML show up across all fields, see [23] [12] [33].…”

Section: Related Workmentioning

confidence: 99%

How to Manage Tiny Machine Learning at Scale: An Industrial Perspective

Ren¹,

Anicic²,

Runkler³

2022

Preprint

View full text Add to dashboard Cite

Tiny machine learning (TinyML) has gained widespread popularity where machine learning (ML) is democratized on ubiquitous microcontrollers, processing sensor data everywhere in real-time. To manage TinyML in the industry, where mass deployment happens, we consider the hardware and software constraints, ranging from available onboard sensors and memory size to ML-model architectures and runtime platforms. However, Internet of Things (IoT) devices are typically tailored to specific tasks and are subject to heterogeneity and limited resources. Moreover, TinyML models have been developed with different structures and are often distributed without a clear understanding of their working principles, leading to a fragmented ecosystem. Considering these challenges, we propose a framework using Semantic Web technologies to enable the joint management of TinyML models and IoT devices at scale, from modeling information to discovering possible combinations and benchmarking, and eventually facilitate TinyML component exchange and reuse. We present an ontology (semantic schema) for neural network models aligned with the World Wide Web Consortium (W3C) Thing Description, which semantically describes IoT devices. Furthermore, a Knowledge Graph of 23 publicly available ML models and six IoT devices were used to demonstrate our concept in three case studies, and we shared the code and examples to enhance reproducibility: Github

show abstract

“…for ML applications that use miniaturized models for extremely energy-efficient inference [28,61]. Further, the lack of a resource-rich Operating Systems (OS) (E.g.…”

Section: Definitionmentioning

confidence: 99%

Intelligence at the Extreme Edge: A Survey on Reformable TinyML

Rajapakse¹,

Karunanayake²,

Nadeem³

2022

Preprint

View full text Add to dashboard Cite

The rapid miniaturization of Machine Learning (ML) for low powered processing has opened gateways to provide cognition at the extreme edge (E.g., sensors and actuators). Dubbed Tiny Machine Learning (TinyML), this upsurging research field proposes to democratize the use of Machine Learning (ML) and Deep Learning (DL) on frugal Microcontroller Units (MCUs). MCUs are highly energy-efficient pervasive devices capable of operating with less than a few Milliwatts of power. Nevertheless, many solutions assume that TinyML can only run inference. Despite this, growing interest in TinyML has led to work that makes them reformable, i.e., work that permits TinyML to improve once deployed. In line with this, roadblocks in MCU based solutions in general, such as reduced physical access and long deployment periods of MCUs, deem reformable TinyML to play a significant part in more effective solutions. In this work, we present a survey on reformable TinyML solutions with the proposal of a novel taxonomy for ease of separation. Here, we also discuss the suitability of each hierarchical layer in the taxonomy for allowing reformability. In addition to these, we explore the workflow of TinyML and analyze the identified deployment schemes and the scarcely available benchmarking tools. Furthermore, we discuss how reformable TinyML can impact a few selected industrial areas and discuss the challenges and future directions.

show abstract

Widening Access to Applied Machine Learning with TinyML

Cited by 22 publications

References 41 publications

Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring

Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring

How to Manage Tiny Machine Learning at Scale: An Industrial Perspective

Intelligence at the Extreme Edge: A Survey on Reformable TinyML

Contact Info

Product

Resources

About