Professional Certificate in Tiny Machine Learning (TinyML)

Course Cover
compare button icon

Course Features

icon

Duration

4 months

icon

Delivery Method

Online

icon

Available on

Limited Access

icon

Accessibility

Desktop, Laptop

icon

Language

English

icon

Subtitles

English

icon

Level

Beginner

icon

Effort

4 hours per week

icon

Teaching Type

Self Paced

Course Description

This exciting Professional Certificate program is offered by Harvard University, Google TensorFlow. You will learn all about Tiny Machine Learning (TinyML), the real-world applications and the future potential of this transformative technology.

TinyML, a cutting-edge field, brings machine learning (ML), to tiny devices and embedded systems. This field requires a deep understanding of algorithms, software, hardware, and applications to be successful.

Fundamentals of TinyML is the first course in the series. It will cover fundamentals of deep and machine learning. This course will help you understand the language of tiny-scale machine learning. Because of the limitations of small devices' energy and memory, this course goes beyond traditional machine learning tools. The second course, Applications of TinyML dives into a variety of applications. You will learn how voice recognition works on small devices, and also see and implement common algorithms like neural networks.

The third course, Deploying TinyML will teach you how to use open-source hardware and prototyping platforms to create your tiny device. The program features projects that are based on the Arduino board–”TinyML Program Kit–”the program emphasizes hands-on training and deployment of machine learning into tiny embedded devices. TinyML Program Kit contains everything you need to unleash your imagination and create applications that use image recognition, audio processing and gesture detection. You'll soon be creating a tiny machine learning application.

This series will teach you how Python (Lite/Micro), the Python programming language, is used to power these devices. It also covers important topics related to responsible design of Artificial Intelligence Systems. These online courses are the first to combine engineering, data science, and computer science. They also feature real-world case studies that show how TinyML deployments can be challenging.

This program was developed in collaboration with Harvard–tm's John A. Paulson school of Engineering and Applied Sciences and the TensorFlow team. This course is taught by Vijay Janapa Reddi from Harvard, Laurence Moroney, Google's Lead AI Advocate, and Pete Warden, the Technical Lead for Google’, TensorFlow, and Micro teams. It offers you an unparalleled opportunity to learn from experts in the AI/machine learning space.

Course Overview

projects-img

International Faculty

projects-img

Case Based Learning

projects-img

Post Course Interactions

projects-img

Case Studies,Instructor-Moderated Discussions

projects-img

Case Studies, Captstone Projects

Skills You Will Gain

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

Course Instructors

Laurence Moroney

Lead AI Advocate

Laurence Moroney leads AI Advocacy at Google, working as part of the Google Research into Machine Intelligence (RMI) team. He's the author of more programming books than he can count, including 'AI a...

Pete Warden

Technical Lead of TensorFlow Mobile and Embedded

Pete Warden is the technical lead of the TensorFlow Micro team at Google, and was previously founder of Jetpac, a deep learning technology startup acquired by Google in 2014. He's one of the original...

Vijay Janapa Reddi

Associate Professor

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 acceler...
Course Cover