HackerTrans
TopNewTrendsCommentsPastAskShowJobs

hardmath123

no profile record

Submissions

A Transformer Quine that generates a lossy copy of its own weights

twitter.com
1 points·by hardmath123·2 tahun yang lalu·0 comments

comments

hardmath123
·tahun lalu·discuss
Here's another blog post on this theme! https://github.com/kach/art-deco/blob/main/art-deco.ipynb
hardmath123
·2 tahun yang lalu·discuss
Re: Low FPS webcam - here's an approach that attempts to analyze coin tossing data from the _sound_ rather than the _video_, since sound is typically recorded at a much higher sampling rate (high enough to "hear" the spinning of the coin). https://cs.stanford.edu/~kach/can-one-hear-the-fate-of-a-coi...
hardmath123
·2 tahun yang lalu·discuss
Relatedly: The Second Eigenvector of the Google Matrix

https://nlp.stanford.edu/pubs/secondeigenvalue.pdf
hardmath123
·2 tahun yang lalu·discuss
A lot of replies here are missing the key idea behind Penrose: that the "substance" and "style" of any mathematical diagram are separable. For example, the "substance" of a diagram might be a collection of sets with known subset relationships:

Set A, B, C

IsSubset(B, A)

IsSubset(C, A)

That same substance can then be rendered in many different styles, e.g. as a Venn diagram or as a tree diagram (substance vs. style is a lot like HTML vs. CSS). Importantly, Penrose's vision is that experts will author libraries of domains and styles, and end-users need only express the substance of their diagrams (i.e. the three lines of code above).

The second beautiful idea in Penrose is that diagram generation is expressed as a constrained optimization problem. This lets you easily experiment with layouts by writing constraints and sampling a variety of potential diagrams via stochastic search.

These two ideas set Penrose apart from most other diagram software out there. I really hope it gains wider adoption. Give it a try!