There has been an M1 fork of Tensorflow almost since the chip launched last year. I believe Apple did the leg work. It’s a hoop to jump through, yes, and no ones training big image models or transformers with this, but I imagine students or someone sandboxing a problem offline would benefit from the increased performance over CPU only.
I was in the hole about 3 years ago, I bought a book, some tools, and a couple of broken movements off of eBay with the thought that I’d just “ dive in and learn how they work “, but I stalled out. Without a set direction I found the space of things that could be wrong with my sample broken movement to be too large. Hell, I didn’t even know if all the components were there.
It’s something I’d like to get into, hopefully with some hand holding. I’m curious what resources you’re using, and if there’s some kind of loose curriculum to ease the beginning efforts.
So I'm likely down the same path as you, eventual "failure", if looking at it as a career choice. But I'm also ~a year behind you, starting a similar path with no handholidng and likely no profit. I watch this guy on youtube, occasionally, and his paid series has been mentioned here and elsewhere, as being worthwhile, but I have not paid for those videos (yet). https://www.watchfix.com/ (formerly known as http://watchrepairlessons.com/ )
B cells also do something called Immunoglobulin class switching to change the structure of antibodies they produce when they encounter their antigen. Different types of antibodies interact with receptors on other cells in the immune system to facilitate the immune response.
https://blog.tensorflow.org/2020/11/accelerating-tensorflow-...