I had a model that I knew wouldn't work. But, I'm coding and my GPUs are idle, so fuck it, right? I kept eye-balling the loss all day *shocked* that it was steadily declining?!
-
-
In my head, my brain is still cheaper than the compute needed to run broad hyper-parameter/structural sweeps/samples. But for how much longer?
-
have long been inspired by this work “Distilling free-form natural laws from experimental data” and have waited for and been inspired to myself plug in the ability to iteratively hypothesize curves and fit them. choose experiments. someone will have tohttps://science.sciencemag.org/content/324/5923/81 …
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
