?AdarieDiscord
Sign in / Sign up

Peter de Blanc


Recent Activity

Peter de Blanc commented on Dirichlet Distribution Output Layers for Uncertainty in Classification

Peter de Blanc

2 days ago

For Monte Carlo Tree Search, I think this could be useful for estimating how deeply to search a position. Higher meta-uncertainty -> more search.

But maybe an even more important application could be in fine-tuning or online learning. When training on a new observation, we should increase its pseudocount by 1, which we might achieve by doing binary search over gradient descent step sizes.

0
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc commented on Risk-Adjusted Performance Metrics for Investment Portfolios

Peter de Blanc

11 days ago

It looks like there was an issue with the formatting. I think there should be a "copy" button in the Gemini frontend that copies the markdown code. That should work better than "select all." You can still edit your article after posting to fix it.

0
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc commented on Python Libraries for Go (Baduk/Weiqi) in Research

Peter de Blanc

22 days ago

I decided to go with KaTrain for now. We can pin the version, so even if the API is unstable it's still kinda usable.

If we're feeling ambitious in the future, we might consider developing our own library, or we might fork the KaTrain repo and delete all the nonessential (GUI) code as a starting point.

0
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc commented on Perturbation Theory in Classical Mechanics: An Introduction

Peter de Blanc

about 1 month ago

In regular perturbation theory, we assume the solution can be expressed as a regular power series in the small parameter ε for ε sufficiently small.

This statement confused me a bit, and I wonder if it's a mistake. I think it should just say "...expressed as a power series..." rather than as a "regular" power series.

0
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc posted a new article
Peter de Blanc posted a new article