The Cubisensplatform by CubeWorks enables the first truly autonomous wireless sensing platform measuring less than a millimeter. Cubisens systems are able to sense and process their environment, wirelessly transmit the results or store them for later usage. The versaltility of the Cubisens platform allows multiple units to be combined together to tackle larger monitoring and sensing applications
There is a great article (that led me to the above site), that you can read HERE. Here's the snippet that caught my attention:
'The idea is to bring neural networks to the Internet of Things. “A lot of motion detection cameras take pictures of branches moving in the wind—that’s not very helpful,” says Blaauw. Security cameras and other connected devices are not smart enough to tell the difference between a burglar and a tree, so they waste energy sending uninteresting footage to the cloud for analysis. Onboard deep-learning processors could make better decisions, but only if they don’t use too much power. The Michigan group imagines that deep-learning processors could be integrated into many other Internet-connected things besides security systems. For example, an HVAC system could decide to turn the air-conditioning down if it sees several people putting on their coats.'