Start with learning what is supervised classification. Yes, those differentiate between car and dog projects are the starter packs. You can’t straight up jump to the problem you have. If you do, you will neither understand not be abl to debug issues you will encounter.

Next , create your training , test and evaluation data. For this, you will need some human experts to look at 1000s of images and label them as “good” or “bad”.

When you have sufficient data read to go, start training an architecture that suits you. Keep tuning it and test it on test data. When you find acceptable performance, go ahead and use it in your production line.

What I said is the rough outline. You need to pad it with courses on theory in probability and calculus at the very list. There are plenty courses in Coursera to start with. And you should definitely not avoid theory and jump straight into the task cause you won’t be able to identify or rectify errors you see during training especially the tricky ones.

Well, this week’s post is created. Respond over there with your paper of the week :)

A woman. I’m interested too… It’s really tiring keeping track of it on an analog Calendar.

If you can’t find anything, I suggest you make her a barebones one or get her to use something like etar. It’s all local.

For sure, sounds interesting !

I am reading ‘attention is not all you need’ https://arxiv.org/abs/2103.03404

I had read this paper in the past but felt the need to refresh my memory and look at self attention with mildly critical lens. Afaik, this paper talks about attention networks without surrounding structures like MLP, skip connections etc and its behaviour.