SwissMAP Logo
Log in
  • About us
    • Organization
    • Professors
    • Senior Researchers
    • Postdocs
    • PhD Students
    • Alumni
  • News & Events
    • News
    • Events
    • Online Events
    • Videos
    • Newsletters
    • Press Coverage
    • Perspectives Journal
    • Interviews
  • Research
    • Field Theory
    • Geometry, Topology and Physics
    • Quantum Systems
    • Statistical Mechanics
    • String Theory
    • Publications
    • SwissMAP Research Station
  • Awards, Visitors & Vacancies
    • Awards
    • Innovator Prize
    • Visitors
    • Vacancies
  • Outreach & Education
    • Masterclasses & Doctoral Schools
    • Mathscope
    • Maths Club
    • Athena Project
    • ETH Math Youth Academy
    • SPRING
    • General Relativity
    • Puzzle Corner
    • Previous Programs
    • Events in Outreach
    • News in Outreach
    • Outreach Resources
    • Exhibitions
  • Equal Opportunities
    • Mentoring Program
    • Financial Support
    • SwissMAP Scholars
    • Events in Equal Opportunities
    • News in Equal Opportunities
  • Contact
    • Corporate Design
    • test
  • News
  • Events
  • Online Events
  • Videos
  • Newsletters
  • Press Coverage
  • Perspectives Journal
  • Interviews

NTK: unlocking the mysteries of deep learning

16 Mar 2021

In 2018, Clément Hongler (EPFL) and his team found a new way of understanding artificial neural networks. It has since then gathered a lot of attention.

 

Clément Hongler and his team from the Chair of Statistical Field Theory found a new way of understanding Artificial Neural Networks. Their 2018 paper has gathered a lot of attention from the scientific community and is now frequently used by researchers when they want to understand the training of large neural networks.

Read article

Text: EPFL News

Research project(s)

  • Statistical Mechanics

ICMP 2021 update: the event will be held as intended

New member: Tatiana Tikhonovskaia (UNIGE, A. Alekseev Group)

  • Leading house

  • Co-leading house


© SwissMAP 2021 - All rights reserved