Applications Kit ML101 - tinyML Starter Kit with Prof. Vijay

Features

• Highly integrated kit: microphone, 3-axis accelerometer, light sensor, 2.4’’ LCD screen, 5- way switch, 1x Grove Ultrasonic sensor , 1x Grove Temperature & Humidity sensor
• Course-in-a-box: exclusive course developed by professor from Harvard University
• From theory to practice: introduces fundamental theory to actual applications of ultra-low power machine learning at the edge
• Extensive use: supports Codecraft graphical programming, Arduino, Micropython,etc

Description

With the motivation of facilitating a bigger population - regardless of their backgrounds - to learn and apply ultra-low power machine learning at the edge to solve the industrial, environmental, social, and economic concerns of our time,  we are honored and excited to collaborate with Professor Vijay Janapa Reddi  of Harvard University on this initiative with generous support from tinyML Foundation and Edge Impulse. 

The initiative provides hardware, learning and hands-on experiences, and custom curriculums to get started with ultra-low power machine learning at the edge.

Hardware - Wio Terminal & Grove

This kit includes 1 Wio Terminal and 2 Grove sensors:  

Wio Terminal is compatible with Arduino and Micropython, built with an ATSAMD51 microcontroller with wireless connectivity supported by Realtek RTL8720DN. Its CPU speed runs at 120MHz (Boost up to 200MHz). Realtek RTL8720DN chip supports both Bluetooth and Wi-Fi providing the backbone for IoT projects. The Wio Terminal is Highly Integrated with a 2.4” LCD Screen, there is an onboard IMU(LIS3DHTR), microphone, buzzer, microSD card slot, light sensor, and infrared emitter(IR 940nm). 

Grove is an open source, modular, easy-to-use toolset optimized for simplicity. The 2 Grove sensors included in the kit are Grove Ultrasonic sensor, Grove Temperature sensor & Humidity sensor. 

With the hardware kit, student experiences, and curated curriculum, you can get hands-on experience, learn about the full circle of Machine Learning algorithms (Data Collection, Pre-processing, Feature Extraction, Model Training, Model Optimizations, ML Model Deployment) whether you are in the classroom, at home, or through distance learning courses, and then you can apply the knowledge to build edge machine learning projects in the real world. 

Course - developed by Prof. Vijay Reddi & Seeed Edu team

Vijay Janapa Reddi is an Associate Professor at Harvard University, Inference Co-chair for MLPerf, and a founding member of MLCommons, a nonprofit ML (Machine Learning) organization aiming to accelerate ML innovation.

A little preview of the course:

Who’s This Book For

This book is designed specifically for educators to be able to adopt the Wio Terminal into the classroom or workshops to show learners the power of edge machine learning. It provides the basic underpinnings that one would have to cover to teach the very basics of ML while keeping the concepts grounded in hands-on exercises. 

Course Structure

This book is specifically designed to serve as a hands-on booklet for teachers and learners for getting started with edge machine learning. Ideally, one would be able to learn the concepts from this book and be able to teach the fundamental concepts of applied machine learning. The keyword is applied as this course focuses on the application of machine learning concepts, rather than on the technical and theoretical aspects of machine learning. 

What You’ll Learn

Users of this book will learn how to train and deploy deep neural network models on Cortex-M core microcontroller devices from Seeed studio. Course content features XXX detailed step-by-step projects that will allow students to grasp basic ideas about modern Machine Learning and how it can be used in low-power and footprint microcontrollers to create intelligent and connected systems.  

After completing the course, the students will be able to design and implement their own Machine Learning enabled projects on Cortex-M core microcontrollers, starting 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. Course content is based on using the Edge Impulse platform, which simplifies data collection/ model training/ conversion pipeline. 

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

About tinyML Foundation

tinyML Foundation is a non-profit professional organization focused on supporting and nurturing the fast-growing branch of ultra-low power machine learning technologies and approaches dealing with machine intelligence at the very edge of the cloud. Seeed is happy and honored to be a Gold Strategic Partner of tinyML Foundation as our way to contribute to serving the emerging community. https://www.tinyml.org/

About Edge Impulse

Edge Impulse is the leading development platform for machine learning on edge devices, free for developers and trusted by enterprises. It’s making building, deploying, and scaling embedded ML applications more accessible and faster than ever, unlocking massive value across every industry. https://www.edgeimpulse.com/

Part List