Very informative and hands-on course for someone new to Embedded Machine Learning domain.

This best thing I liked about course is that you don't have to purchase any new embedded hardware. You can use your smartphone as a hardware and perform all experiments on it.

Thanks for creating this course, it really helped me in gaining knowledge of Embedded ML.

Excellent course with great foundational knowledge about machine learning on edge devices using your smart phone and the Arduino Nano 33 BLE Sense for hands-on, real world, applications that are enabled on the Edge Impulse machine learning platform. Shawn did an excellent job putting together the course curriculum and presented a complete and comprehensive set of knowledge, including lectures given by Alexander on machine learning and artificial intelligence, and also information and 'labs' for students to complete that made it easy to apply the concepts taught in this course. I highly recommend this course using the Arduino Nano 33 BLE Sense for real world applications if you'd like to know what's under the hood of embedded IoT devices. 👍

As everybody says they go at a really fast pace, I had to watch like three times each video, but the content is really good and concise. Thanks to the sponsors and to the teacher

Very good arrange of topics and explain complex topics as simply as possible. Recommended course for anyone who needs to start in embedded machine learning.

May be good for beginners, but as someone with previous ML knowledge it was quite boring. Was hoping for a greater focus on the embedded side.

Thanks for detailed and well introduced topics, I enjoyed this course. I had prior knowledge in neural networks but this course was awsome for introducting ML for microcontrollers.

This is an exceptional introduction to machine learning on embedded devices.

The material covers all the bases and leaves you with a very good idea of what is involved. The use of Edge Impulse allows rapid prototyping of machine learning solutions so the course is able to walk you through two working examples, a movement gesture classifier and an audio keyword classifier, that you can deploy to either a mobile phone or an Arduino board. In addition two projects allow you to have a go for yourself.

Whilst the course doesn't delve too much into the heavy theory it does provide plenty of resources where you can look for additional information. It also includes a wealth of top tips that will help you with your ML projects.

A very good intro to TinyML generally and its use in conjunction with Edge Impulse - also a bit of exposure to Google Colab.

Good things:- The practical work / examples were interesting and fun. The "further reading" material was interesting too.

Less good things:- The downloadable lecture notes leave a bit to be desired, but making notes during the lecture is easy enough. Getting the software (node.js, chocolatey etc) was harder work than anything on the course!

An excellent course to step into the world of embedded machine learning and TinyML. Despite being a 3 week course, it manages to fit in a lot of relevant content including ML basics, sensor data processing, and feature selection.

The instructors do a great job of clearly communicating the concepts without assuming any prior knowledge of Embedded Systems and Machine Learning. The teaching materials used are also top-notch and effective.

The Course is really Helpful for me. It just gave me a good and basic idea of where to start if i want to implement machine learning in the microcontroller.

ML on embedded systems is an exciting and growing technology and business domain. This course is a great place to start learning about it.

Excellent, excellent course. As usual, Shawn Hymel is a great instructor; clear, engaging, fun. To be honest, I enrolled in this course because he was the instructor. I ended up buying the Arduino TinyML kit, which contains a camera and a board to plug both, the camera and the Arduino nano 33 BLE sense ***LITE***. I emphasize the kit contains the LITE version of the board, rather than nano 33 BLE sense.... The LITE version does not have the humidity sensor.... If you don't notice that, and you try to compile an example that uses the HTS221 the LITE board does not have, you will spend some time debugging.... It's all good... part of the learning process...

Please keep in mind, this course is an "Introduction to ...."; the key word is "introduction". Some people complained the course was too easy for them. Of course, if one has a lot of background before taking the course, the course may feel "easy". I knew a lot of the material presented, but still enjoyed it; if nothing else, you will experience a great presentation. ;-)

I consider as an amazing course for someone who does not know about Machine Learning, with the video classes and the reference lectures, it is possible to get a good introduction about a lot of important things that the machine learning science has to offer to solve different problems into industry and now-a-day need with the current and new technology that have today. With the EDGE IMPULSE platform is possible to work quickly with machine learning implementation and get a good practical idea about the potential that machine learning has to solve different problems, and understand the different concept that that science has.

Awesome content. As a learner can expect to go from 0 to 100% on your first steps into machine learning. You only need your cellphone and some time to finish the homeworks. This course is a 50/50 split between teory and practice, so you must be warned that you will be teached by doing stuff. At the end of this course you will have a good grasp of AI, ML and how to develop and deploy them using a cellphone (or an arduino).

This should be your first step if you are considering to start learning about AI, or if you know about it, but you want to have experience deploying your AIs.

This is a great introduction to ML and especially to ML. I like how it walked us through some small projects using the Edge Impulse tool. This makes it practical and fun. Shawn Hymel obviously knows what he is doing and knows what he is talking about. But he also teaches on a level that is useful for a range of audiences. Much of it was a review for me, because I had studied ML several years ago. But this class has good stuff for the beginner and for the reviewer alike. Of course, the novelty of it is the embedded part. Thanks so much for a great class!

This course was very useful. I am not new to Machine Learning and microcontrollers and have been developing tinyML models. I have even been playing with EdgeImpulse, but this course teaches you the whole machine learning data pipeline from data collection. through data cleaning, train/validation/test split, data augmentation, feature engineering, model creation, model training and tuning, fixing fitting problems and finally, deploying the solution to your hardware.

It helped me to see the process as a whole!

Thanks a lot!

This course dives you through the basic knowledge of embedded machine learning. The way instructor Shawn Heyml taught the course was just awesome. The most interesting thing about this course was that some concepts were taught by the experts in their respected domains. If you are looking for some new course in the embedded systems domain then this course is perfect for you. I would like to thank my instructor Mr. Shawn Heyml who have done great efforts to clear each and every concept through this course.

"I am extremely impressed with the level of expertise and hands-on experience the embedded machine learning course provided. The instructors not only taught the theory behind the concepts, but also demonstrated their practical application through hands-on exercises. Additionally, the course made it easy for me to familiarize myself with the components without needing any specialized equipment, as we used our own smartphones for the labs. Overall, a fantastic learning experience!"

Even if a bit fast for people completely without a machine learning background, the topics in this well structured course are well chosen and explained in a way even someone like me would understand. The mix of theory and practice makes this course a nice experience you don't want to miss if you are interested in topics like machine learning, embedded systems, neural networks or audio classification.

The explanations are concise and clear, and there is no need for prior experience in machine learning, as the concepts are explained before they are used / deployed.

There are review questions at the end of videos and there are review quizzes to get a better grasp on the material. This type of attention to detail alongside the quality of the course material made this one of my all-time favorites.

If you are already familiar with machine learning, then this course will be an interesting addition to your skills. In this course, you will understand how audio classification works, how to collect data from microcontroller sensors and how to work with the Edge Impulse platform. An interesting introductory course in Embedded Machine Learning!

Very info packed but impactful overview of Machine Learning for Embedded systems, can't wait to review the materials again and begin to apply these ideas to my projects. I'm much more confident using Edge Impulse now as well. The follow along project videos were incredibly helpful for practical learning.

Very good course! I've started this course having absolute zero knowledge about AI, machine learning and related stuff. Now, I can say I do know the basics of AI and machine learning, allowing (and encouraging) me to deep dive into these areas to make more and more interesting embedded systems projects..

Embedded ML made easy with EdgeImpulse. Good course for those who want a straightforward path into Embedded ML. The course is structured to get you started with all the valuable aspects of getting the ML on an Embedded System. I learnt a lot even though I had an ML course during my formal education.

This course added a lot of knowledge. It exposes basic machine learning definitions, from data preparation to evaluation metrics. The edge platform is shown, which works as a means for obtaining data until the machine learning model is downloaded, both for embedded systems and for smartphones.