Fundamentals of TinyML from edX

What do you know about TinyML? Tiny Machine Learning (TinyML) is one of the fastest-growing areas of Deep Learning and is rapidly becoming more accessible. This course provides a foundation for you to understand this emerging field.

TinyML is at the intersection of embedded Machine Learning (ML) applications, algorithms, hardware, and software. TinyML differs from mainstream machine learning (e.g., server and cloud) in that it requires not only software expertise, but also embedded-hardware expertise.

The first course in the TinyML Certificate series, Fundamentals of TinyML will focus on the basics of machine learning, deep learning, and embedded devices and systems, such as smartphones and other tiny devices. Throughout the course, you will learn data science techniques for collecting data and develop an understanding of learning algorithms to train basic machine learning models. At the end of this course, you will be able to understand the “language” behind TinyML and be ready to dive into the application of TinyML in future courses.

Following Fundamentals of TinyML, the other courses in the TinyML Professional Certificate program will allow you to see the code behind widely-used Tiny ML applications—such as tiny devices and smartphones—and deploy code to your own physical TinyML device. Fundamentals of TinyML provides an introduction to TinyML and is not a prerequisite for Applications of TinyML or Deploying TinyML for those with sufficient machine learning and embedded systems experience.

What's inside

Learning objectives

Fundamentals of machine learning (ml)
Fundamentals of deep learning
How to gather data for ml

How to train and deploy ml models
Understanding embedded ml
Responsible ai design

Fundamentals of machine learning (ml)
Fundamentals of deep learning
How to gather data for ml
How to train and deploy ml models
Understanding embedded ml
Responsible ai design

Syllabus

Chapter 1: Welcome to TinyML

Chapter 1.1: Course Overview

Chapter 1.2: The Future of ML is Tiny and Bright

Chapter 1.3: TinyML Challenges

Chapter 1.4: Getting Started

Chapter 2: Introduction to (Tiny) ML

Chapter 2.1: The Machine Learning Paradigm

Chapter 2.2: The Building Blocks of Deep Learning

Chapter 2.3: Exploring Machine Learning Scenarios

Chapter 2.4: Building a Computer Vision Model

Chapter 2.5: Responsible AI Design

Chapter 2.6: Summary

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

For students curious about the intersection of ML, deep learning, embedded devices/systems

Covers fundamentals of both ML and DL

Taught by two instructors who hold esteemed positions in the field, ensuring high-quality instruction

Provides a strong foundation required for future courses in the TinyML Professional Certificate program

Explores industry-relevant applications of TinyML

Covers responsible AI design principles to promote ethical use of AI applications

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Fundamentals of TinyML with these activities:

Refresh ML Fundamentals

Show steps

Review the fundamentals of ML to bridge any gaps in your knowledge and ensure a smoother learning experience in TinyML.

Browse courses on Machine Learning

Show steps

Review key ML concepts such as data preprocessing, model training, and evaluation.
Go over foundational algorithms like linear regression, logistic regression, and decision trees.
Practice implementing simple ML models using a programming language like Python.

Read 'TinyML: Machine Learning with Tiny Devices and Edge Computing'

Show steps

Gain a comprehensive understanding of TinyML concepts and applications by exploring this authoritative text.

View TinyML: Machine Learning with TensorFlow Lite... on Amazon

Show steps

Read through the book's chapters, focusing on the fundamentals of TinyML.
Work through the examples and exercises provided in the book.
Summarize the key concepts and techniques discussed in the book.

Join a TinyML Study Group

Show steps

Collaborate with peers to enhance your understanding and problem-solving skills.

Browse courses on TinyML

Show steps

Find or create a study group with other students enrolled in the TinyML course.
Set regular meeting times to discuss course material, work on assignments together.
Share knowledge, ask questions, and provide feedback to fellow group members.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Solve ML Coding Challenges

Show steps

Engage in practical exercises to solidify your understanding of ML concepts and algorithms.

Browse courses on Machine Learning

Show steps

Find online ML coding challenges or use platforms like LeetCode or Kaggle.
Attempt to solve challenges involving data preprocessing, model training, and evaluation.
Analyze your solutions, identify areas for improvement, and learn from your mistakes.
Share your solutions and insights with peers or mentors for feedback.

Connect with TinyML Experts

Show steps

Seek guidance and support from experienced professionals in the field.

Browse courses on TinyML

Show steps

Attend industry events or join online communities related to TinyML.
Reach out to researchers, engineers, or practitioners in the field.
Request mentorship or guidance on specific TinyML topics or projects.

Follow Online TinyML Tutorials

Show steps

Supplement your learning with guided tutorials to reinforce concepts and gain practical insights.

Browse courses on TinyML

Show steps

Search for online tutorials and courses on TinyML offered by platforms like Coursera, Udemy, or edX.
Select tutorials that align with your learning goals and skill level.
Follow the tutorials step-by-step, completing exercises and assignments.
Use the tutorials as a reference resource for future projects or assignments.

Build a TinyML Project

Show steps

Apply your TinyML knowledge to a practical project, reinforcing your understanding and developing your skills.

Browse courses on TinyML

Show steps

Identify a problem or need that can be addressed using TinyML.
Design and develop a TinyML solution using appropriate hardware and software.
Train and deploy your TinyML model on the target device.
Evaluate the performance of your TinyML solution and make improvements as needed.

Contribute to TinyML Open-Source Projects

Show steps

Engage with the TinyML community and contribute to real-world projects.

Browse courses on TinyML

Show steps

Explore open-source TinyML projects on platforms like GitHub or GitLab.
Identify projects that align with your interests and skill level.
Contribute to projects by submitting bug reports, suggesting features, or writing code.
Collaborate with other developers and learn from their experiences.

Career center

Learners who complete Fundamentals of TinyML will develop knowledge and skills that may be useful to these careers:

Machine Learning Engineer

A Machine Learning Engineer specializes in the engineering aspects of machine learning, and combines knowledge of software programming with a deep understanding of machine learning models and algorithms. They work on developing, deploying, and maintaining machine learning systems. Knowledge of model deployment, training, and data gathering, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Machine Learning Engineer

Software Engineer

Software Engineers apply engineering principles to the design, development, deployment, and maintenance of software systems. They can work on projects that range from web to mobile to enterprise applications. Knowledge of embedded ML, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Software Engineer

Data Scientist

A Data Scientist combines knowledge of mathematics, statistics, and computer science to tackle business problems. They work on everything from data cleaning and data analysis to the creation of machine learning models, and are often tasked with explaining complex technical concepts to non-technical stakeholders. Knowledge of model training, data gathering, and responsible AI design, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Data Scientist

Embedded Systems Engineer

An Embedded Systems Engineer designs, develops, and tests embedded systems, which are computer systems that are designed to be part of a larger system. These systems are often used in industrial, medical, and automotive applications. Knowledge of embedded ML, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Embedded Systems Engineer

Deep Learning Engineer

Deep Learning Engineers are responsible for designing, developing, and deploying deep learning models. They work on a wide range of projects, from image recognition to natural language processing. The deep learning fundamentals taught in Fundamentals of TinyML can help someone succeed in this career.

See salaries and explore the career path for Deep Learning Engineer

Data Analyst

Data Analysts use data to solve business problems. They work on everything from data cleaning and data analysis to the creation of visualizations. Knowledge of data gathering, responsible AI design, and model deployment, as taught in Fundamentals of TinyML, can help someone succeed in this role.

See salaries and explore the career path for Data Analyst

Artificial Intelligence Engineer

An Artificial Intelligence Engineer designs, develops, and deploys AI systems. They work on a wide range of projects, from self-driving cars to medical diagnosis systems. Fundamentals of TinyML provides an introduction to the fundamentals of machine learning and deep learning, which are essential for success in this field.

See salaries and explore the career path for Artificial Intelligence Engineer

Machine Learning Researcher

A Machine Learning Researcher develops new machine learning algorithms and techniques. They work on a wide range of problems, from fraud detection to medical diagnosis. Knowledge of model training, data gathering, and responsible AI design, as taught in Fundamentals of TinyML, can help someone succeed in this role.

See salaries and explore the career path for Machine Learning Researcher

Operations Research Analyst

Operations Research Analysts use mathematical and analytical techniques to solve business problems. They work on a wide range of projects, from supply chain management to healthcare operations. Knowledge of data gathering, model training, and responsible AI design, as taught in Fundamentals of TinyML, can help someone succeed in this role.

See salaries and explore the career path for Operations Research Analyst

Statistician

Statisticians collect, analyze, and interpret data. They work on a wide range of projects, from clinical trials to market research. Knowledge of data gathering, responsible AI design, and model training, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Statistician

Data Engineer

Data Engineers design, build, and maintain data pipelines. They work on a wide range of projects, from data integration to data warehousing. Knowledge of data gathering, model deployment, and responsible AI design, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Data Engineer

Quantitative Analyst

Quantitative Analysts use mathematical and statistical techniques to analyze financial data. They work on a wide range of projects, from risk management to portfolio optimization. Knowledge of data gathering, model training, and responsible AI design, as taught in Fundamentals of TinyML, can help someone succeed in this role.

See salaries and explore the career path for Quantitative Analyst

Business Intelligence Analyst

Business Intelligence Analysts use data to make better business decisions. They work on everything from market research to financial analysis. Knowledge of data gathering, responsible AI design, and model deployment, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Business Intelligence Analyst

Robotics Engineer

Robotics Engineers design, develop, and test robots. They work on a wide range of projects, from industrial robots to medical robots. Knowledge of embedded ML, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Robotics Engineer

Product Manager

Product Managers are responsible for the development and launch of new products. They work on everything from market research to product design. Knowledge of responsible AI design, as taught in Fundamentals of TinyML, can help one succeed in this role.

See salaries and explore the career path for Product Manager