Features

• Hardvard University Professor. Reddi Course Revise
• Simple and understandable Machine Learning Theory
• Easily get started with hand-on TinyML labs
• Additional ultrasonic, temperature and humidity measured sensor
• Powerful embedded terminal: Wio Terminal

Description

The future of Machine Learning is tiny and bright, as the topic sentence of the Harvard University TinyML course, indicates that Machine Learning deployed in tiny devices and embedded systems have become an innovative field and possess a promising future. Successful AI deployment in this field requires intimate embedded system and Machine Learning knowledge of applications, algorithms, hardware, even software, all of which sometimes are difficult to manage, especially for beginners. 

In this case, for the most simple machine learning comprehending, we are thrilled to publish the TinyML Starter Kit with Wio Terminal, parceled the course which is jointly developed by Harvard Professor theoretical curriculum and Seeed hands-on Wio Terminal-based project labs. There are additional Grove-Temperature & Humidity and Grove-Utrasonic in the Kit and beginners can apply them to hands-on exercise,

such as Gesture recognition using Wio Terminal built-in light sensor, Motion Recognition using built-in accelerometer, and more.

The advent of TinML Starter Kit course offers a new thread for beginners to establish the basic concepts of machine learning through the concise hands-on deployment of ML models. The pivot of this course is enabling beginners to be able to design and implement their own embedded Machine Learning projects on the Wio Terminal. Hardware kits that support this book ensure the exercises are simple enough for beginners via the Wio Terminal integrated system and Grove assemble electronics. 

 Furthermore, course content is based on using the Edge Impulse platform, which simplifies machine learning processes data collection/ model training/ conversion pipeline. In the end, beginners can start from defining a problem to gathering data and training the neural network model and finally deploying it to the device to display inference results or control other hardware appliances based on inference data.

About Wio Terminal

Wio Terminal is a real AI platform built around the ATSAMD51P19 and ARM Cortex-M4F at 120MHz for high compatibility with various edge ML frameworks with numerous peripherals and pinouts, supporting Microsoft Azure IoT Central, Edge Impulse development platform, and Tensorflow Lite model. 

With wireless connection Bluetooth & Wi-Fi, built-in Microphone & Buzzer, flexible 5 switch way button, and functional 3 Axis accelerometer, light sensor, displaying on the LCD screen, the Wio Terminal sustains its strength in the TinyML field, supporting the whole course project while students learning. 

Curriculum

Students will receive the basic ideas of Artificial Intelligence, Machine Learning, Deep Learning from the course first.

Then the course will introduce machine learning approaches for embedded systems including Tiny Machine Learning which becomes increasingly popular. For each Machine Learning approach, there are supported by machine learning algorithms where they can be summarized as three major classes. Hence, in the following course, students will be able to learn these three major classes of machine learning algorithms as supervised, unsupervised, and reinforcement machines. 

Finally moreover most importantly, the course describes the lifecycle of the Machine Learning algorithms that it contains Data Collection, Pre-processing, Feature Extraction, Model Training, Model Optimizations, ML Model Deployment. Course content features detailed step-by-step projects that will allow students to utilize this theory knowledge and deploy them as functioning models in low-power and footprint microcontrollers, encouraging students to create intelligent and connected systems with Wio Terminal by themselves. 

Get free access to the course by scanning QR code on the box. 

Course outline

Application

• Individual: A perfect start of knowing Machine Learning field and a great experience of increasing hands-on ability.
• Educational institution: An ideal solution for comprehensive and understandable Machine Learning methods teaching, focused on hands-on experiments.

There are more interesting projects, application and information about TinyML you can obtain at the bottom.

Part List