NAM2019
  • NAM2019
    • Registration
    • Key Dates & Outline Schedule
    • Practical Information
    • Exhibitors
    • Grants & Bursaries
    • Contacts
  • Science
    • Science Programme
    • Parallel Sessions
    • Plenary Talks
    • Community Session
    • Special Lunches
    • Posters
    • Presenter Guidelines
  • Social
    • What's On
    • Welcome Reception
    • RAS Awards Dinner
  • Media
  • Outreach
    • Outreach and Education Day
    • Fringe Event
    • School Visit Day
  • Lancaster
    • Travel
    • Accommodation
    • Childcare
    • Campus Map
    • About Lancaster
    • Code of Conduct
  • NAM2019
    • Registration
    • Key Dates & Outline Schedule
    • Practical Information
    • Exhibitors
    • Grants & Bursaries
    • Contacts
  • Science
    • Science Programme
    • Parallel Sessions
    • Plenary Talks
    • Community Session
    • Special Lunches
    • Posters
    • Presenter Guidelines
  • Social
    • What's On
    • Welcome Reception
    • RAS Awards Dinner
  • Media
  • Outreach
    • Outreach and Education Day
    • Fringe Event
    • School Visit Day
  • Lancaster
    • Travel
    • Accommodation
    • Childcare
    • Campus Map
    • About Lancaster
    • Code of Conduct

Poster

id
Transfer learning for radio galaxy
MachineLearning
Hongming
Tang
Date Submitted
2019-03-12 13:08:50
Jodrell Bank Centre for Astrophysics, the University of Manchester
A. Hongming Tang (JBCA) B. Anna Scaife (JBCA) C. J.P. Leahy (JBCA)
In the context of radio galaxy classification, most state-of-the-art neural network algorithms have been focused on single survey data. The question of whether these trained algorithms have cross-survey identification ability or can be adapted to develop classification networks for future surveys is still unclear. One possible solution to address this issue is transfer learning, which re-uses elements of existing machine learning models with different applications. Here we present radio galaxy classification based on a 13-layer Deep Convolutional Neural Network (DCNN) using transfer learning methods between different radio surveys. We find that our machine learning models trained from a random initialization achieve accuracies comparable to those found elsewhere in the literature. When using transfer learning methods, we find that inheriting model weights pre-trained on FIRST images can boost model performance when re-training on lower resolution NVSS data, but that inheriting pre-trained model weights from NVSS and re-training on FIRST data impairs the performance of the classifier. We consider the implication of these results for future radio surveys being planned for next-generation radio telescopes such as ASKAP, MeerKAT, and SKA1-MID.

RAS Logo

Lancaster University Logo

STFC logo

Science Programme

  • Monday
  • Tuesday
  • Wednesday
  • Thursday
  • Posters

All attendees are expected to show respect and courtesy to other attendees and staff, and to adhere to the NAM Code of Conduct. To report harassment or violation of the code of conduct please click here.

© 2022 Royal Astronomical Society

Login