Machine Learning(ML) is a dynamic and powerful field of computer science that has permeated nearly every digital thing that we interact with even household appliances. This is because many state-of-the-art machine learning models require significant computing resources and power consumption to perform inference, which is the act of running the ML models and making predictions about its inputted data. The need for high-performance computing resources has confined many ML applications to the cloud, where compute at the data center level is readily available. To allow ML to broaden its reach, and unlock a new era of applications in the process, we must find ways to facilitate ML inference on smaller, more resource-constrained devices. This pursuit has led to the field known as Tiny Machine Learning.
Tiny ML Applications whether you realize it, Tiny ML is probably a part of your daily life in some capacity. Applications for Tiny ML include: keyword spotting object recognition and classification gesture recognition audio detection machine monitoring An example of a Tiny ML application in daily life is the audio wake-word detection model used inside of Google and Android devices.
Hardware Used in Tiny ML Applications : When it comes to the hardware side of things, Tiny ML is impressive in that it aims to work on some pretty unimpressive hardware. From a certain perspective, the real goal of Tiny ML is to perform ML inference at the lowest power possible. Pete Warden, widely considered the father of Tiny ML, states in his seminal book on the subject that Tiny ML should aim to operate at a power consumption below 1 mW. The reason for this seemingly arbitrary number is that 1 mW consumption makes a device capable of running on a standard coin battery with a reasonable lifetime of months to a year. So when you think about power sources for Tiny ML, think of coin batteries, small Li-Po batteries, and energy harvesting devices. From a computer perspective, Tiny ML doesn’t rely on graphic processing units (GPU), application-specific integrated circuits (ASIC), and microprocessors like most ML applications.
To meet the lofty 1 mW goals, we are almost exclusively confined to less capable computing hardware like microcontrollers (MCU) and digital signal processors (DSP). These devices are often Cortex-M based and can be expected to have no more than a few hundred KB of RAM, similar amounts of flash, and clock speeds in the tens of MHz. Beyond this, other hardware you might expect to find on a Tiny ML device includes sensors.
Benefits of Tiny ML The main benefit of Tiny ML is its portability: Running on cheap microcontrollers with tiny batteries and low power consumption means that, using Tiny ML, one can easily integrate ML into virtually anything for cheap. Benefits On top of this, Tiny ML also has the benefit of increased security due to the local nature of the computing—i.e, data doesn’t need to be sent to the cloud.With a solid introduction to the field of Tiny ML, we can now dive deeper into more technical aspects of the field in the next article.
You must be logged in to post a comment.