Siamese Neural Network predicts critical phenomena in 3D percolation models

Researchers have developed a novel Siamese Neural Network (SNN) designed for label-efficient prediction of critical phenomena in 3D percolation models. This framework accurately identifies phase transitions and critical exponents using minimal labeled data, even generalizing to different lattice structures without retraining. The SNN autonomously learns to quantify cluster size, demonstrating its potential for criticality detection in data-scarce environments where explicit order parameters are undefined. AI

IMPACT This research demonstrates a novel approach for applying machine learning to complex scientific problems, potentially accelerating discovery in fields like statistical physics.

RANK_REASON The cluster contains a research paper published on arXiv detailing a new machine learning model for a specific scientific problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• 3D percolation models
• arXiv
• bond percolation
• face-centered cubic lattices
• machine learning
• percolation theory
• Shanshan Wang
• Siamese Neural Network
• simple cubic lattices
• site percolation
• statistical physics

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →