Welcome to the Arduino Deep Learning From Ground Up™ .
We are going to embark on a very exciting journey together. We are going to learn how to build deep neural networks from scratch on our Arduino.
We shall begin by learning the basics of deep learning with practical code showing each of the basic building blocks that end up making a giant deep neural network. All of this on our Arduino, both training and inference.
As we begin to deal with large datasets we shall start training our neural networks on our computers and then deploying the the trained models on our microcontrollers. Due to the limited memory and processing power of Arduino we shall learn methods for quantizing our models before deploying them on our resource constrained Arduino without compromising the accuracy of our models.
We shall also learn how to thoroughly take advantage of deep learning libraries such as Keras and Tensorflow as well as Arduino specific deep learning libraries such as TensorFlow Lite.
By the end of this course you will be able to build neural networks from scratch without libraries, be able to master quantization methods for deploying neural networks on microcontrollers, be able to build deep learning Arduino projects for Image Classification, be able to build deep learning Arduino projects for gesture recognition,be able to build deep learning Arduino projects for speech recognition and so much more.
If you are new to machine learning and deep learning, this course is for you. The course starts from the very basic building block of neural networks and teaches you how to build your own neural network using pure c code before we move on to see how to use readily available libraries.
If you already have some experience with deep learning and want to see how to deploy models on Arduino you can also join this course. This course gives an in-depth training on the design methodology that needs to be adopted in order to be to deploy models on resource constrained Arduino.
Sign up and lets start building some intelligent firmware.