Skip to main content

Embedded Machine Learning on Edge Devices

Daniel Situnayake talks about his work with EdgeML, the biggest challenges in embedded machine learning, potential use cases of machine learning models in edge devices, and the best tips for aspiring machine learning engineers and data science practitioners to get started with embedded machine learning.  

Aug 2022
View Transcript

Key Quotes

Until now, machine learning has been something that’s been constrained to giant, one-size-fits-all models that are running in the cloud at big tech companies’ data centers, but now we are able to compress machine learning down into smaller and smaller devices so it can fit more neatly into the little corners of our lives. It democratizes machine learning so that we can have smaller models that are trained by people who are working in all corners of the world, whether it's in some niche industry or a place that has particular problems that can be addressed with machine learning. It’s actually a lot more feasible to get great performance out of these tinier models in smaller contexts, rather than trying to create these giant models that do everything.

There is a huge opportunity to build tools and adapt tool chains that can empower people who are experts in their own niche fields to utilize embedded machine learning without having to take years to study the field and learn the ins and outs of data science and machine learning.

Key Takeaways


You can start learning about embedded machine learning by building an awareness of the relationship between the size of models and the amount of resources they consume. By tinkering with that relationship, you can start exploring model compression and quantization.


Embedded machine learning has a huge challenge to overcome: because all the data is trapped at the edge of the network and the device is what’s interpreting it, there isn’t an efficient way to check whether the model is working properly or not.


The most important work is in opening up access to people, enabling them to understand the machine learning workflow without being a machine learning expert and building tools to easily understand things like sensor data and that give meaningful feedback.

About Daniel Situnayake

Photo of Daniel Situnayake
Daniel Situnayake

Daniel Situnayake is the Founding TinyML Engineer and Head of Machine Learning at Edge Impulse, a leading development platform for embedded machine learning used by over 3,000 enterprises across more than 85,000 ML projects globally. Dan has over 10 years of experience as a software engineer, which includes companies like Google (where he worked on TensorFlow Lite) and Loopt, and co-founded Tiny Farms America’s first insect farming technology company. He wrote the book "TinyML", and the forthcoming "AI at the Edge".

Photo of Richie Cotton
Richie Cotton

Richie helps organizations get from a vague sense of "hey we ought to get better at using data" to having realistic plans to become successful data-driven organizations. He's been a data scientist since before it was called data science, and has written several books and created many DataCamp courses on the subject.


How to Become a Data Scientist in 8 Steps

Find out everything you need to know about becoming a data scientist, and find out whether it’s the right career for you!

Jose Jorge Rodriguez Salgado

12 min

How Data Science is Changing Soccer

With the Fifa 2022 World Cup upon us, learn about the most widely used data science use-cases in soccer.
Richie Cotton's photo

Richie Cotton

Top Machine Learning Use-Cases and Algorithms

Machine learning is arguably responsible for data science and artificial intelligence’s most prominent and visible use cases. In this article, learn about machine learning, some of its prominent use cases and algorithms, and how you can get started.
Vidhi Chugh's photo

Vidhi Chugh

15 min

Inside the Generative AI Revolution

Martin Musiol talks about the state of generative AI today, privacy and intellectual property concerns, the strongest use cases for generative AI, and what the future holds.

Adel Nehme's photo

Adel Nehme

32 min

A Complete Guide to Data Augmentation

Learn about data augmentation techniques, applications, and tools with a TensorFlow and Keras tutorial.
Abid Ali Awan's photo

Abid Ali Awan

15 min

Understanding Text Classification in Python

Discover what text classification is, how it works, and successful use cases. Explore end-to-end examples of how to build a text preprocessing pipeline followed by a text classification model in Python.
Moez Ali 's photo

Moez Ali

12 min

See MoreSee More