Last year, my father-in-law got a trail cam at my suggestion – mainly to get pictures of the rats that were eating his compost. It worked:

I borrowed it a while back, and finally set it up today under our bird feeder to see what we could get. Not a bad haul! We got:

• Spotted towhees:

• Dark-eyed juncos:

• Black and grey squirrels:

• A chickadee:

Not bad!

Out for radio as well: 12 QSOs from the North American QSO contest, including D4Z from Cape Verde – about 9150km on 10W. Nice!

My project: critiquing your dishwasher loading technique using machine learning. A work in progress. You can find the repo here.

I’ve been interested in machine learning for a while now. Like a lot of things, my approach has been a bit scattered. I’m slowly learning how to get better at that, but I still tend to veer around.

A couple of months ago, I decided to take the Fast.ai course again. I had done a couple of lessons a year ago, but had not followed it up. This time around, I saw that they not only had a new version of the course, but a book as well. I ordered the book (and another book as well), and got started on the Jupyter notebooks that the book is based on.

Let’s see where this goes!