Real numbers, data science and chaos: How to fit any dataset with a single parameter · HackerPapers discussions

Real numbers, data science and chaos: How to fit any dataset with a single parameter — mentioned by bmc7505

Wed, 26 Apr 2023 00:38:09 GMT

With arbitrary-precision, you can essentially replace the entire neural network with a single trainable parameter. [1] Likewise, in model checking, one often uses bounded-length bitvectors, because even a PDA with two stacks is Turing-equivalent. The poor separability between theoretical and physically-realizable models of computation is one of the weaknesses of the Chomsky hierarchy and classical approximation theory, and why more descriptive theories to characterize function complexity, e.g., circuit complexity, algebraic complexity theory and/or logical expressivity, are often needed. [1]…

Paper and discussion history. A mention is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — mentioned by vladoh

Mon, 17 Jan 2022 22:24:09 GMT

This is a very interesting idea, even if not really practical. The author has more details in the paper: https://arxiv.org/abs/1904.12320

Paper and discussion history. A mention is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — mentioned by chuckee

Mon, 18 Oct 2021 10:36:57 GMT

The Bertelsmann Foundation wants to promote social integration and diversity. It advocates for creating a "comprehensive and long-term migration architecture" for Germany. - https://en.wikipedia.org/wiki/Bertelsmann_Stiftung#Society But as the sibling comment notes, in other areas they're not at all left-leaning, e.g.: Arvato, a division of the Bertelsmann Group, declared the privatization of public services a strategic business area. It should not surprise anyone that characterizing their politics on a one-dimensional left-right spectrum is inaccurate (findings such as…

Paper and discussion history. A mention is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — HN submission

Wed, 29 Sep 2021 18:50:12 GMT

How to fit any dataset with a single parameter

217 points; 146 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — HN submission

Wed, 22 May 2019 22:02:54 GMT

How to approximate any dataset with a single parameter [pdf]

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — mentioned by stevesimmons

Fri, 10 May 2019 06:32:32 GMT

> For any arbitrarily complex curve, I think I can give you a 1D parameterization for it. If you haven't see it already, read this paper by Laurent Boue: "Real numbers, data science and chaos: How to fit any dataset with a single parameter" https://arxiv.org/abs/1904.12320

Paper and discussion history. A mention is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — HN submission

Tue, 07 May 2019 11:18:52 GMT

Data science and chaos: How to fit any dataset with a single parameter

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Real numbers, data science and chaos: How to fit any dataset with a single parameter — HN submission

Fri, 03 May 2019 10:14:15 GMT

How to fit any dataset with a single parameter

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.