Skip to content

  • Home
  • The collaboration
    • People
    • Institutes
    • Structure
  • Research
    • Global QCD analysis and machine learning
    • General strategy
    • Data
    • Neural Networks
    • Minimization
    • Cross-validation
    • Closure testing
    • Future testing
    • Hyperparameter Scan
    • Current research
  • For users
    • NNPDF code
    • Unpolarized PDF sets
    • Polarized PDF sets
    • Nuclear PDFs
    • Fragmentation functions
    • Neutrino Structure Functions
    • Tools
  • Documents
    • Papers
    • Talks
    • Lectures
    • Theses
    • Schools
  • Media
  • For the public

Search

Methodology

Methodology

Short-term goals

  • PDF parametrization
    • Fit preprocessing
    • Neural network architecture:
      • Single-layer for each PDF
      • One single (multilayer or perhaps deep) NN for all PDFs
  • Minimization algorithms
    • CMA algorithm: validation
      • Closure test
      • Check against reweighting
      • Check of positivity
    • CMA algorithm: optimization
      • Grid search

 


 

Mid- to long-term goals

  • Minimization algorithms
    • CMA algorithm: optimization
      • Gradient-based methods
    • Weight minimization + other new methods

About Accepta

Accepta is a modern, responsive WordPress theme designed for businesses, portfolios, and blogs.

About WPDINO

WPDINO is a WordPress development company. We create beautiful, functional themes that help businesses grow online.

Quick Links

  • Home
  • About
  • Services
  • Contact
  • Privacy Policy

Search

LinkedIn
© 2026 . Powered by WordPress.

NNPDF privacy and cookies

Our website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Please visit our Privacy and cookies page for more information about cookies and how to disable them.

Close