Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Identifying polymer states by machine learning.

Qianshi Wei1, Roger G Melko1,2, Jeff Z Y Chen1

  • 1Department of Physics and Astronomy, University of Waterloo, Waterloo N2L 3G1, Canada.

Physical Review. E
|April 19, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Probing Defects with Quantum Simulator Snapshots.

Physical review letters·2026
Same author

Artificial intelligence for quantum computing.

Nature communications·2025
Same author

Hierarchical ground-state crystals underlying Hertzian quasicrystals.

Nature communications·2025
Same author

Transitional patterns on a spherical surface: from scars to domain defects of mixed lattices.

Soft matter·2025
Same author

Phase-field model for quantitative analysis of droplet wetting.

Soft matter·2025
Same author

Conditioned quantum-assisted deep generative surrogate for particle-binary vector indicating thecalorimeter interactions.

NPJ quantum information·2025

This study shows that feed-forward neural networks can effectively classify polymer configurations and identify phase transition points. This offers a novel computational approach for analyzing polymer behavior.

Area of Science:

  • Polymer Science
  • Computational Chemistry
  • Machine Learning

Background:

  • Understanding polymer configurations and phase transitions is crucial in materials science.
  • Traditional methods for analyzing polymer states can be computationally intensive.

Purpose of the Study:

  • To explore the capability of feed-forward neural networks (FNNs) in classifying diverse polymer configurations.
  • To investigate the use of FNNs for identifying phase transition points in polymeric systems.

Main Methods:

  • Numerical experiments were conducted using a simple feed-forward neural network model.
  • The network was trained to recognize distinct polymer structures: gaslike coil, liquidlike globular, and crystalline (anti-Mackay and Mackay).
  • The network's ability to identify transition points was validated against independent specific-heat calculations.

Related Experiment Videos

Main Results:

  • The trained neural network successfully classified multiple polymer configurations.
  • The identified transition points closely matched those determined by specific-heat calculations.
  • Demonstrated the efficacy of neural networks in recognizing different polymer states.

Conclusions:

  • Feed-forward neural networks offer an effective and unconventional tool for studying polymer phase transitions.
  • This approach provides a computationally efficient alternative for analyzing complex polymer systems.
  • Highlights the potential of machine learning in advancing polymer science research.