MACHINE LEARNING tinyml . org
“ This will create a better , healthier and more sustainable environment for all ”
EVGENI GOUSEV CHAIRMAN , TINYML FOUNDATION .
( with mW or less power consumption ), algorithms and models - smaller ( down to 10s of kB of memory requirements ), software – lighter down to deployment on deeply embedded platforms . This enormous wave of technological innovation and fast growing tinyML ecosystem creates a strong momentum towards new applications and business opportunities .”
Better latency , better interactivity and less power usage Gabriel Aguiar Noury , Product Manager at Canonical , says that edge computing is
important to assist with the next industrial revolution . He said : “ Our ways of working demand low latency and the need to deliver data in real-time . To reduce latency and costs , companies are quickly moving their computing power to the edge , leaning less on data centres that could be situated far away . A part of this evolution is tiny machine learning , otherwise known as TinyML .
By using TinyML , there is no need to use cloud services to process this data , which means better latency , better interactivity , and less power usage . The technology can be implemented in cheaper devices , such as smartphones , and empower them to assist with more intelligent activities while continually learning to improve the process . Examples include swarm robotics that can explore collapsed underground mines , or store shelves that can be replenished when required .”
technologymagazine . com 123