user avatar
Miles Cranmer
@MilesCranmer
Assistant Prof @Cambridge_Uni, works on AI for the physical sciences. Previously Flatiron, DeepMind, Princeton, McGill.
Cambridge, UK
astroautomata.com
Joined September 2011
1,007
Following
13.9K
Followers
Posts
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Sep 29, 2021
    John von Neumann: "with four parameters I can fit an elephant" Meanwhile, this paper arxiv.org/abs/1904.12320: "How to fit any dataset with a single parameter" Here's a function with a *single* parameter. Even worse: it's differentiable and continuous!
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Jun 23, 2020
    Very excited to share our new paper "Discovering Symbolic Models from Deep Learning with Inductive Biases"! We describe an approach to convert a deep model into an equivalent symbolic equation. Blog/code: astroautomata.com/paper/symbolic… Paper: arxiv.org/abs/2006.11287 Thread👇 1/n
  • user avatar
    Miles Cranmer
    @MilesCranmer
    May 4, 2023
    Three years ago, I started working on an easy-to-use tool for interpretable machine learning in science. I wanted it to do for symbolic regression what Theano did for deep learning. Today, I am beyond excited to share with you the paper describing it! arxiv.org/abs/2305.01582 1.
    00:00
    240K
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Jul 12, 2020
    Here's a condensed version of the matplotlib cheatsheets so it can fit a desktop background (github.com/matplotlib/che…) Full image: drive.google.com/file/d/1kwYFaR… and vectorized .svg, with the non-standard fonts outlined: drive.google.com/file/d/1b2LtZU… Thanks @NPRougier et al for making it!
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Mar 28, 2024
    It's crazy how over time I have slowly replaced all of my command line tools with Rust equivalents 🦀 - cat → bat - pip → uv - grep → ripgrep - htop → zenith - fswatch → watchexec Any other good ones?
    311K
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Mar 7, 2022
    Could machine learning rediscover the law of gravitation simply by observing our solar system? With our new approach, the answer is *YES*. Led by: @PabloLemosP With: @Niall_Jeffrey @cosmo_shirley @PeterWBattaglia Paper: arxiv.org/abs/2202.02306 Blog: astroautomata.com/paper/rediscov…
    00:00
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Oct 16, 2020
    If you’ve never tried it, playground.tensorflow.org is the single best explanatory tool for neural networks. An essential demo for any deep learning course! I still notice improvements in my intuition just by tinkering with it. From @dsmilkov @ShanCarter.
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Feb 23, 2023
    Life update: this fall I will be joining the University of Cambridge as Assistant Professor! I will be appointed as joint faculty between DAMTP and the Institute of Astronomy 🚀
    (Pajor Pawel – King's College and the River Cam)
    203K
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Oct 9, 2023
    I'm super excited to share a new initiative I am a part of! Announcing: Polymathic AI 🎉 We are developing foundation models for scientific *data*, such that they can leverage shared concepts across disciplines. polymathic-ai.org 1/6
    425K
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Jun 17, 2022
    Today I learned you can write numbers like this in Python (!!) Makes it easier to read long numbers by separating digits into groups, just like 1,000,000. It’s so esoteric that Google Colab doesn’t even color it correctly!
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Aug 5, 2020
    A matplotlib trick that I wish I learned a long time ago: To adjust resolution of figures, rather than using plt.figure(figsize=(8, 8)) followed by a tweaking of every font size, you can just increase the resolution with: plt.figure(dpi=300)
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Oct 12, 2022
    Amazing. VSCode LaTeX Workshop has dark mode for *PDFs*! It even inverts the figures! github.com/James-Yu/LaTeX…
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Sep 23, 2023
    I'm starting a curated list of interactive machine learning demos: github.com/MilesCranmer/a…. Looking for more suggestions! My plan is to incorporate some into the ML modules of Cambridge's new MPhil in Data Intensive Science, as a way to hone students' intuition.
    00:00
    139K
  • user avatar
    Miles Cranmer
    @MilesCranmer
    Feb 26, 2025
    Why 'I don’t know' is the true test for AGI—it’s a strictly harder problem than text generation! This magnificent 62-page paper (arxiv.org/abs/2408.02357) formally proves AGI hallucinations are inevitable, with 50 pages (!!) of supplementary proofs.
    91K