About the Series
Introducing the second season of WILDLABS Tech Tutors, our series that focuses on answering the "how do I do that?" questions of conservation tech. Launched with the support of Microsoft AI for Earth, this series will give you the bite-sized, easy-to-understand building blocks you'll need to broaden your conservation technology horizons, enhance your research, or launch a new collaborative project.
Taking place every Thursday, each Tech Tutor will present a 30 minute tutorial guiding you through an aspect of conservation tech, followed by a 30 minute live Q&A session with the audience.
Tech Tutors is made for conservation tech beginners of all knowledge levels (and yes, even experts can still be beginners when it comes to tackling a new aspect of conservation tech or starting a new project!), and because we know that there's always more to learn in the #tech4wildlife world, that's why we're so excited to bring you a brand-new season of WILDLABS Tech Tutors! With presentations that will take you even deeper into those tricky "how do I do that?" questions of conservation tech, we hope you'll discover new perspectives and ideas to bring to your own #tech4wildlife work.
For participants, the outcome will be an increased sense of confidence in their technological skills, the ability to actively build off of the skills discussed in these tutorials, and an opportunity to learn and collaborate with other members of the WILDLABS community. Read about the first season's community highlights here.
Our goal is to customize these tutorials to fit the needs of the community and address your needs, so let us know what you want to see in this season and beyond.
Can't make it? You can find every tutorial after it airs on our Youtube channel.
Meet your Tutor: Daniel Situnayake, Edge Impulse
Dan leads embedded machine learning engineering at Edge Impulse, a platform that allows any developer to train machine learning models that run on tiny, low-power devices. He's the author of the O'Reilly book TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers, leads embedded machine learning development at Edge Impulse Inc., and helps organize the global TinyML meetup community. He has previously worked on the TensorFlow team at Google, as CEO of Tiny Farms Inc., and as a lecturer in Automatic Identification and Data Capture technologies at Birmingham City University.
We asked Dan...
What will I learn in this episode?
You'll learn the concept of MLOps and why it is so important to the success of machine learning projects. You'll learn how to apply it to your own work using tools like Edge Impulse, an MLOps platform for training embedded machine learning models.
How can I learn more about this subject?
Google have an extremely detailed breakdown of the concept of MLOps here.
To learn more about Edge Impulse, visit edgeimpulse.com.
Check out my previous WILDLABS Tech Tutors episode 'How do I train my first Machine Learning model?' for an end to end workshop on training a conservation model using Edge Impulse.
If I want to take the next step, where should I start?
I'd recommend trying some of the tutorials in the Edge Impulse documentation which will walk you through the process of training a model:
- Edge Impulse: Continuous motion recognition
- Edge Impulse: Audio classification
- Edge Impulse: Image classification
What advice do you have for a complete beginner in this subject?
Contrary to popular belief, you don't need to know advanced mathematics to use machine learning. Unless you're a researcher developing new machine learning algorithms, you're absolutely fine with high-school level maths (and you won't even need that very often). The key to learning is to build projects and look up what you need to know along the way. End-to-end tools like Edge Impulse help a lot with this since they abstract away the technology —meaning you can focus on the problem you are trying to solve.
Additional resources from the episode
- WILDLABS AI for Conservation Group
- UCL is starting a module on ecology and ML, and they're looking for collaborators
-
The board Dan used in his tutorial: Himax HX6537-A WE-I Plus
-
List of boards supported by Edge Impulse
-
UMAP user guide: Uniform Manifold Approximation and Projection for Dimension Reduction
-
List of acoustic software and their differing functionalities from Tessa Rhinehart
-
Book: Building Machine Learning Powered Applications: Going from Idea to Product
-
Edge Impulse blog: Run image classification in a containerized environment with BalenaCloud
-
Tutorial: Running your Edge Impulse locally through WebAssembly
A new Coursera course on machine learning from Edge Impulse is coming soon!
Find out what the audience members are working on and look for collaborations - view the participant check in here.
Learn more about our upcoming Tech Tutorials
Visit the series page on WILDLABS to find the full list of WILDLABS Tech Tutors.
Add the first post in this thread.