دانلود کتاب دستی بر TinyML – استفاده از قدرت یادگیری ماشینی در دستگاه های لبه

TinyML is an emerging trend in machine learning, that aims at deploying complex machine learning and neural network models on low-powered tiny edge devices and microcontrollers. Modern deep learning algorithms are computationally expensive and result in large model size. They are often hosted on dedicated servers having enormous computing resources. As users, we generate the data at our end and send them via the internet to process remotely. Owing to the limitations in network bandwidth, roughly 10% of all our data can be sent over the internet. Processing of the data on the edge can revolutionize the current paradigm. Thanks to TinyML, large machine learning models can be shrunk in order to effectively deploy on smaller devices having few hundred kilobytes of RAM and few megabytes of flash memory. Such devices can operate 24×7 with a minimum power consumption. Moreover, being entirely offline, the applications not only consumes zero network bandwidth, but also preserves user privacy. TinyML is going to be the next big thing in machine learning. Major tech giants are heavily investing in standardizing the hardware and software stack. In this book, we cover the basic concepts of TinyML through practical coding examples to enable the readers to learn the basic concepts of TinyML and develop their own applications. Rather than discussing every single mathematical concept behind the machine learning algorithms, the book primarily focuses on end-to-end application development through coding examples. The projects covered in this book are implemented in open-source software commonly used in industry and academics.