Top all-time · #19947
cgad.ski
Personal blog · cgad.ski/blogmathaiscience
cgad.ski is a personal blog at cgad.ski about math, ai and science. Since 2022, 3 different Hacker News readers have linked it 19 times, most often “A coin flip by any other name (2023)”. It is still writing: the last post was on 2026-08-31, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
Only one comment is available, and it discusses physics-informed neural networks while citing Wikipedia. It does not assess the site's writing.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- A coin flip by any other name (2023)2 people · 3 mentions · first linked 2023-09-26
- Where is Noether's principle in machine learning?2 people · 2 mentions · first linked 2024-03-01
What Hacker News says?
I had two design goals for my tiny personal page: * Write the content in Markdown. * Don't require any source files to update it. And here we are: https://cgad.ski .
Comment linking /
on “Ask HN: Share your personal site”Submitted Where is Noether's principle in machine learning? as a story · 296 points
HN discussionThere's a lot of beautiful writing on these topics on the "pure math" side, but it's hard to figure out what results are important for deep learning and to put them in a form that doesn't take too much of an investment in pure math. I think the first chapter of [1] is a good introduction to general facts about high-dimensional stuff. I think this is where I first learned about "high-dimensional oranges" and so on. F…
Comment linking /blog/when-numbers-are-bits.html
on “Language models pack billions of concepts into 12k dimensions”Submitted Entropy of a Mixture as a story · 54 points
HN discussionI don't think so? Wikipedia suggests that "Physics-informed neural networks" is > a type of universal function approximators that can embed the knowledge of any physical laws that govern a given data-set in the learning process https://en.wikipedia.org/wiki/Physics-informed_neural_networ... In other words, that seems to refer to giving the model prior info (a bias) about physical laws that generated the data. What I…
Comment linking /blog/where-is-noethers-principle-in-machine-learning.html
on “Physics-Based Deep Learning Book”Submitted A coin flip by any other name (2023) as a story · 53 points
HN discussionhttps://cgad.ski
Comment linking /
on “Ask HN: Could you share your personal website here?”Submitted How efficient are distributed codes? as a story · 4 points
HN discussionSubmitted Backprop Isn't Just for Calculus as a story · 3 points
HN discussionSubmitted Backprop isn't just for calculus as a story · 3 points
HN discussionSubmitted A Note on Scale-Free Networks as a story · 3 points
HN discussionSubmitted When numbers are bits: distributed representations for sets as a story · 1 points
HN discussionSubmitted When Gradient Descent Is a Kernel Method as a story · 1 points
HN discussionSubmitted A Coin Flip by Any Other Name as a story · 1 points
HN discussionSubmitted A Coin Flip by Any Other Name... as a story · 1 points
HN discussionSubmitted What Is Dimensional Analysis? as a story · 1 points
HN discussionSubmitted The Central Binomial Coefficient and Laplace's Method as a story · 1 points
HN discussionSubmitted The Central Binomial Coefficient and Laplace's Method as a story · 1 points
HN discussionSubmitted What Is Dimensional Analysis? as a story · 1 points
HN discussion