Go back to the [[AI Glossary]]
In TensorFlow, a value or set of values calculated at a particular step, usually used for tracking model metrics during training.
supervised machine learning
Training a model from input data and its corresponding labels. Supervised machine learning is analogous to a student learning a subject by studying a set of questions and their corresponding answers. After mastering the mapping between questions and answers, the student can then provide answers to new (never-before-seen) questions on the same topic. Compare with unsupervised machine learning.
Don’t seem to have journalled much in the garden this week.
I think partly I’ve gotten a little distracted by the stream.
There has been a new wave of Mastodon users and usage thanks to the possibility of [[Elon Musk’s takeover of Twitter]].
Which is cool, and meant I’ve been a bit more active there. Feels like the new people brings a new diversity of content. Less niche stuff in a way.
But also I still think stream-y microblogging is not the social media of choice for me. Or maybe just one component of it. Great for networking and connecting, but (for me) a bit too much of a time sink and not good for deep engagement.
Keeping up to date with local activities, but annoyed by how it’s all on Twitter and Facebook. Thinking about some kind of [[Municipalist social media]].
Had a go with the [[telescope]].