Introduction to TinyML
Introduction to TinyML (aka Tiny Machine Learning) is ML or AI (aka Artificial Intelligence) running in small devices like a "genie in a bottle". And the fun thing about this book is it talks about fun gadgets like person detection on $20 devices that can be made smart by grandma or a elementary schooler with a FREEly available no-code platform http://cainvas.ai-tech.systems/ in a few clicks or touch buttons. For instance, a 8 year old can build "hey google" smart speaker (aka keyword spotting) in less than 10 minutes, just by saying "keyword" a few times.
Make no mistake, author is a super technocrat and author of deep tech software like https://github.com/ai-techsystems/deepC and founder of two companies. He built the AI and ML technology targeted towards devices with small formfactor like microcontrollers, which are part of all sorts of household devices: think appliances, cars, and toys. In fact, there are around 30 billion microcontroller-powered devices produced each year. They're cheap, require very little energy, and are very reliable.
By bringing deep learning models to tiny microcontrollers, we can boost the intelligence of billions of devices that we use in our lives, without relying on expensive hardware or reliable internet connections. Imagine smart appliances that can adapt to your daily routine, intelligent industrial sensors that understand the difference between problems and normal operation, and magical toys that can help kids learn in fun and delightful ways.
No comments:
Post a Comment