Tiny Machine Learning (TinyML)

What you will learn

• Fundamentals of machine learning, deep learning, and embedded devices.
• How to gather data effectively for training machine learning models.
• How to use Python to train and deploy tiny machine learning models.
• How to optimize machine learning models for resource-constrained devices.
• How to conceive and design your own tiny machine learning application.
• How to program in TensorFlow Lite for Microcontrollers.
• There are hundreds of billions of microcontrollers today, and an increasing desire to deploy machine learning models on these devices through TinyML. Learners who complete this program will be prepared to dive into this fast-growing field.
• Learners will have a fundamental understanding of TinyML applications and use cases and gain hands-on experience in programming with TensorFlow Micro and deploying TinyML models to an embedded microprocessor and system.

Program Overview

In this exciting Professional Certificate program offered by Harvard University and Google TensorFlow, you will learn about the emerging field of Tiny Machine Learning (TinyML), its real-world applications, and the future possibilities of this transformative technology.

TinyML is a cutting-edge field that brings the transformative power of machine learning (ML) to the performance- and power-constrained domain of tiny devices and embedded systems. Successful deployment in this field requires intimate knowledge of applications, algorithms, hardware, and software.

This first course in this series, Fundamentals of TinyML, will teach you the fundamentals of machine and deep learning. In this course, you will understand the language of tiny machine learning, which goes beyond the traditional machine learning toolkit due to the energy and memory constraints of tiny devices. The second course, Applications of TinyML, dives into an array of applications, where you will see how tools like voice recognition works in practice on small devices and you can see and implement common algorithms such as neural networks.

The third course, Deploying TinyML, will give you a chance to use an open source hardware and prototyping platform to build your own tiny device. Featuring projects based on an Arduino board—TinyML Program Kit—the program emphasizes hands-on experience with training and deploying machine learning into tiny embedded devices. The TinyML Program Kit has everything you need to unlock your imagination and build applications around image recognition, audio processing, and gesture detection. Before you know it, you’ll be implementing an entire tiny machine learning application.

Throughout the series, you will learn how the Python programming language using TensorFlow (Lite/Micro) is used to power these devices as well as important topics in the responsible design of Artificial Intelligence systems. These first-of-their-kind online courses combine data science, computer science, and engineering to feature real-world application case studies that examine the challenges facing TinyML deployments.

This program is a collaboration between expert faculty at Harvard’s John A. Paulson School of Engineering and Applied Sciences (SEAS) and innovative members of Google’s TensorFlow team. Taught by Harvard Professor Vijay Janapa Reddi, Lead AI Advocate at Google, Laurence Moroney, and Technical Lead of Google’s TensorFlow and Micro team, Pete Warden, this course offers you the unique opportunity to learn from leaders in the AI and machine learning space.

Courses in this program

Fundamentals of TinyML

Focusing on the basics of machine learning and embedded systems, such as smartphones, this course will introduce you to the “language” of TinyML.

Applications of TinyML

Get the opportunity to see TinyML in practice. You will see examples of TinyML applications, and learn first-hand how to train these models for tiny applications such as keyword spotting, visual wake words, and gesture recognition.

Deploying TinyML

Learn to program in TensorFlow Lite for microcontrollers so that you can write the code, and deploy your model to your very own tiny microcontroller. Before you know it, you’ll be implementing an entire TinyML application.

Job Outlook