Holding On

We may have entered the “lean times” with my blogging and learning. To be fair, I took the kids skiing this weekend, and knew I was going to have a few days of no ML. And I did manage to get off my butt this morning (Monday, w/ holiday) and start Geron Chapter 12 (Custom Models and Training with TensorFlow). But I’m sensing echoes of past attempts that went off the rails. It is so crucial to diligently stay ON TASK, and do at least a little EVERY DAY. Similar to diet/exercise (which I’m also trying to keep on course!)

So long story short, today’s study was a nudge in the right direction. In the future, I should plan for light/leisurely ML reading if I’m going to be on vacation. Keep the flywheel spinning, if you will.

Not much to share as far as things learned/read, although I did come across an article about converting Russian speech to text this morning. Most of the ML details went over my head, but the gist was these scientists are trying to pragmatically advance the state of the art (and publicly available) models/science around Speech to Text, specifically in Russian. They also take umbrage to the need to put everything in a peer-reviewed, scientific article. My interpretation was “stop being so formal - move fast, break things, and learn from our mistakes”. I like it.

I need to read more random ML articles/libraries/whatever in future. Broad strokes to expand my horizons.

Upcoming Week

Working through Chapter 12 and taking notes. I’m a bit concerned that the book is working through a swamp of TensorFlow minutia, and it’s easy to lose focus there. I may need to attempt some side adventures of ML readings and learnings to keep things interesting.