Seeking Your Feedback on Roadtesting an Artificial Intelligence Eval kit

With your talents, hopefully you can find a new job quickly.

I've played with some AI-focused boards in the past, and so far one thing that is *very* important to test, is what the workflow looks like when it comes to training models. I remember one specific board where all the training had to be done on a proprietary cloud platform where you had to upload the training data, set inputs and outputs, and it would do the training for you. It didn't have a lot of options and the whole process was a black box. The output was an obfuscated binary that had to be uploaded to the board. Training and testing models was a truly miserable experience. And I could never see the whole thing working because the board died in one of the many steps of the process.

On the other hand I also played with a board that had some level of compatibility with pytorch models, and that made it a lot easier to do all the tinkering, training and testing on my PC, and then just upload the trained model to the board.

So the "training new models" workflow is what I'd love to test.
That, and performance.

EDIT: I see that the toolkit and platform for AI training is mentioned in the description, btw, and I know most of that toolchain is designed to make things easier for users, but I'd be interesting in checking whether the experience is closer to the first example I mentioned, or the second. And whether it's possible to do more traditional learning and then connect that somehow to their toolchain.

Very interesting device to get familiar with AI/ML. There is a lot more to learn with this unit than just concepts. The amount of new components, that I don't even recognize on the PCB, is amazing (3,4,7,8,8,16,18,19,21,). Or maybe they just used AI to generate the list of parts/features on top and bottom of the board.  

Areas where we have success with AI:

Production optimisation: prepare plan to say what we should produce, where and when, to have enough stock for customers. With the best use of resources

Route optimisation for store delivery. Wat orders should we combine on what truck, and what route should they take, for the most efficient store replenishment

Me too !

I do a lot of work with sensors. Currently I'm working on a project where the customer want every hardware and software design decision to be traceable back to it's origins, cross referenced to the specifications and justified by testing or logic.

I can't quite see where ML fits in this (and similar) scenarios.

MK

This looks super cool.  My fear is that I would not be able to learn a new ecosystem in time to complete the roadtest.   I see this as ripe for a fall detection application.

Oh no, are you leaving your cool kitchen with smart range hood behind?

This would be a fun one to play with! I’m in the middle of a big move (Wisconsin over to Michigan) so don’t have the time available… :( 

Interesting device. Infineon recently announced AI targeted PSoC Family: https://www.infineon.com/cms/en/product/microcontroller/32-bit-psoc-arm-cortex-microcontroller/32-bit-psoc-edge-arm/

but on this board there is still old good PSoC 6.

This would be a fun project to road test I currently have a Google Coral and a few LLM's I created but the coral is more difficult to use. I would like to see how this product performs compared to the coral I also like the fact that it has many built-in sensors and IMAGIMOB Studio this will really streamline creation of LLM's.