We promote and support the development of machine learning technologies and applications including hardware, algorithms and software capable of performing on-device sensor data analytics at extremely low power, typically for battery operated devices.
Tiny machine learning is the fast-growing field of machine learning technologies and applications including hardware, algorithms, and software capable of performing on-device sensor (vision, audio, IMU, biomedical, etc.) data analytics. Operating at extremely low power, typically in the milliwatt range and below, this technology enables a variety of always-on use-cases for battery operated devices. Recent developments reveal that: (i) tiny machine learning capable hardware is becoming “good enough” for many commercial applications and new architectures (e.g. in-memory compute) are on the horizon; (ii) significant progress on algorithms, networks and models down to 100kB and below; and (iii) initial low power applications in the vision and audio space. There is growing momentum demonstrated by technical progress and ecosystem development. Join the growing tinyML community at our frequent events including tinyML Summit, tinyML EMEA, tinyML Asia, tinyML Talks, and tinyML Meetups.
Download content from this year’s Event Partners.