The Shed

DATA MODEL FOR EMBEDDED MACHINE LEARNING

In The Shed Issue No. 105, we saw how machine learning (ML) could be embedded in a smart device such as the Arduino Nicla board. The following steps can be taken to activate the prediction features in our board:

1. Acquire data through sensors — usually part of the ML board creating a collection of samples.

2. Use the samples to define the data model with the ML platform — like Neuton.AI in our case.

3. Test the model with sample data on the platform using the Web.

4. Generate the software to embed the prediction features in the ML microcontroller.

5. Run the prediction offline on the programmed ML microcontroller.

This sounds very impressive, but a final problem arises: how to manage the microcontroller sensors to

You’re reading a preview, subscribe to read more.

More from The Shed

The Shed11 min read
A Use For Leftover Forged Cranks
The story of Chris Gordon making a seatless tricycle from components inexpensively sourced from Christchurch’s EcoShop was related in part 1 of “Chris Gordon keeps busy” – The Shed, issue 113. A consequence of buying several second-hand children’s bi
The Shed2 min readDiscrimination & Race Relations
OK, Boomer!
I’m a boomer. I was born in that exalted era between the end of World War II and 1964. I was a rebel, a hippy, a rock music fan. I grew up during one of the longest sustained periods of peace and prosperity. That changed when the Americans brought us
The Shed7 min read
The Best Hut Ever!
My six-year-old grandson, Mars, has been diagnosed as autistic. With his birthday coming up, I decided to build him a hut – one that could go outside or in the garage; one where he could do whatever he wanted to and it wouldn’t be a problem. Mars lik

Related