Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Is Canadian AI failing? | BetaKit

Perplexity AI’s Plan for Search Ads Looks Nothing Like Google

Reka launches Nexus, an AI workforce powered by its state-of-the-art multimodal reasoning model | Taiwan News

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • Amazon (Titan)
    • Anthropic (Claude 3)
    • Cohere (Command R)
    • Google DeepMind (Gemini)
    • IBM (Watsonx)
    • Inflection AI (Pi)
    • Meta (LLaMA)
    • OpenAI (GPT-4 / GPT-4o)
    • Reka AI
    • xAI (Grok)
    • Adobe Sensi
    • Aleph Alpha
    • Alibaba Cloud (Qwen)
    • Apple Core ML
    • Baidu (ERNIE)
    • ByteDance Doubao
    • C3 AI
    • DataRobot
    • DeepSeek
  • AI Research & Breakthroughs
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Education AI
    • Energy AI
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Media & Entertainment
    • Transportation AI
    • Manufacturing AI
    • Retail AI
    • Agriculture AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
Facebook X (Twitter) Instagram
Advanced AI News
Yannic Kilcher

Discovering Symbolic Models from Deep Learning with Inductive Biases (Paper Explained)

Advanced AI EditorBy Advanced AI EditorMay 12, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email



Neural networks are very good at predicting systems’ numerical outputs, but not very good at deriving the discrete symbolic equations that govern many physical systems. This paper combines Graph Networks with symbolic regression and shows that the strong inductive biases of these models can be used to derive accurate symbolic equations from observation data.

OUTLINE:
0:00 – Intro & Outline
1:10 – Problem Statement
4:25 – Symbolic Regression
6:40 – Graph Neural Networks
12:05 – Inductive Biases for Physics
15:15 – How Graph Networks compute outputs
23:10 – Loss Backpropagation
24:30 – Graph Network Recap
26:10 – Analogies of GN to Newtonian Mechanics
28:40 – From Graph Network to Equation
33:50 – L1 Regularization of Edge Messages
40:10 – Newtonian Dynamics Example
43:10 – Cosmology Example
44:45 – Conclusions & Appendix

Paper:
Code:

Abstract:
We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations. We find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark matter simulation-and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures. The symbolic expressions extracted from the GNN using our technique also generalized to out-of-distribution data better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn.

Authors: Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, Shirley Ho

Links:
YouTube:
Twitter:
Discord:
BitChute:
Minds:

source

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleStarlink launch in India gains momentum with new spectrum rules
Next Article US, China agree to reduce tariff rates for 90 days
Advanced AI Editor
  • Website

Related Posts

Yannic Kilcher Live Stream

May 27, 2025

Imagination-Augmented Agents for Deep Reinforcement Learning

May 27, 2025

Learning model-based planning from scratch

May 27, 2025
Leave A Reply Cancel Reply

Latest Posts

UK MPs to Debate Banning Advertising by Oil Companies

Albright College is Selling Its Art Collection to Balance Its Books

Big Three Auction Houses Hold Old Masters Sales in London This Week

MFA Boston Returns Two Works to Kingdom of Benin

Latest Posts

Is Canadian AI failing? | BetaKit

July 7, 2025

Perplexity AI’s Plan for Search Ads Looks Nothing Like Google

July 7, 2025

Reka launches Nexus, an AI workforce powered by its state-of-the-art multimodal reasoning model | Taiwan News

July 7, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Is Canadian AI failing? | BetaKit
  • Perplexity AI’s Plan for Search Ads Looks Nothing Like Google
  • Reka launches Nexus, an AI workforce powered by its state-of-the-art multimodal reasoning model | Taiwan News
  • Germany demands App Store ban over data violations
  • Huawei-Alibaba Clash Heats Up On AI Model Plagiarism Allegations – Alibaba Gr Hldgs (NYSE:BABA)

Recent Comments

No comments to show.

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

YouTube LinkedIn
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.