Results 171 to 180 of about 2,597 (210)

TinyML Meets IoT: A Comprehensive Survey

Internet of Things (Netherlands), 2021
Abstract The rapid growth in miniaturization of low-power embedded devices and advancement in the optimization of machine learning (ML) algorithms have opened up a new prospect of the Internet of Things (IoT), tiny machine learning (TinyML), which calls for implementing the ML algorithm within the IoT device .
Lachit Dutta
exaly   +2 more sources

Is TinyML Sustainable?

Communications of the ACM, 2023
Assessing the environmental impacts of machine learning on microcontrollers.
Shvetank Prakash, Matthew Stewart, Colby R. Banbury, Mark Mazumder, Pete Warden, Brian Plancher, Vijay Janapa Reddi   +6 more
openaire   +1 more source

Earthquake Detection with tinyML

Seismological Research Letters, 2023
Abstract Earthquake detection is the critical first step in earthquake early warning (EEW) systems. For robust EEW systems, detection accuracy, detection latency, and sensor density are critical to providing real-time earthquake alerts.
openaire   +3 more sources

Software frameworks for TinyML

Bharat S Chaudhari, Marco Zennaro
exaly   +2 more sources

IP Protection in TinyML

2023 60th ACM/IEEE Design Automation Conference (DAC), 2023
Jinwen Wang, Yuhao Wu, Han Liu, Bo Yuan 0002, Roger D. Chamberlain, Ning Zhang 0017   +5 more
openaire   +1 more source

Special Issue on TinyML

IEEE Micro, 2023
Vijay Janapa Reddi, Boris Murmann
openaire   +1 more source

TMM-TinyML

Proceedings of the 28th Annual International Conference on Mobile Computing And Networking, 2022
Bharath Sudharsan, Sonu Prasad, Dan Jose, John G. Breslin   +3 more
openaire   +1 more source

TinyML in Africa: Opportunities and Challenges

2021 IEEE Globecom Workshops (GC Wkshps), 2021
Samson Otieno Ooko, Marvin Muyonga Ogore, Jimmy Nsenga, Marco Zennaro   +3 more
openaire   +1 more source

TinyML Acceleration with MAX78000

The advancement of edge devices equipped with specialized hardware accelerators has brought the deployment and execution of Deep Neural Network (DNN) models nearer to users and real-world sensor systems. This paper investigates the potential of the MAX78000 microcontroller in accelerating Tiny Machine Learning applications, which require real-time ...
Dabbous A., Lazzaroni L., Bellotti F., Presentacion S. M., Pighetti A., Berta R.   +5 more
openaire   +1 more source

Work in Progress: Linear Transformers for TinyML

2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)
We present the WaveFormer, a neural network architecture based on a linear attention transformer to enable long sequence inference for TinyML devices. Waveformer achieves a new state-of-the-art accuracy of 98.8 % and 99.1 % on the Google Speech V2 keyword spotting (KWS) dataset for the 12 and 35 class problems with only 130 kB of weight storage ...
Scherer M., Cioflan C., Magno M., Benini L.   +3 more
openaire   +1 more source