| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • You already know Dokkio is an AI-powered assistant to organize & manage your digital files & messages. Very soon, Dokkio will support Outlook as well as One Drive. Check it out today!

View
 

ML_Meetings_2020

Page history last edited by Kieran 3 years, 2 months ago

Machine Learning in Astronomy Meetings

 

Regular fortnightly (i.e. every 2 weeks) informal zoom research meetings take place on https://uws.zoom.us/j/6448448129 and on the WSU Kingswood campus in room Y2.32 (the "Thinktorium"). Times were chosen by a Doodle poll, and will be revisited every 6 months.

 

Schedule of Meetings in 2020: 

  • 04/02/2020 1100 (AEDT) - Nic Ralph (ICNS in the MARCS Institute at WSU): "An Introduction to Neuromorphic Engineering, and how it fits into Astronomy and Machine Learning" . Download Link. Youtube Link.
  • 18/02/2020 2000 (AEDT) - Rafael Mostert (Leiden) - Preliminary Results on Region-CNN's for Radio Source Component Association. Download Link. Youtube link.
  • 03/03/2020 1100 (AEDT) - Jacky Thong (CSIRO's Data61 and University of Melbourne) - Infrared Host Galaxy Identification using GANs without Training Labels. Download Link. Youtube Link. Slides Link.
  • 17/03/2020 2000 (AEDT) - Tim Galvin (CSIRO): "Attempts to Catalogue the Radio Sky using PINK". Download Link. Youtube Link.
  • 31/03/2020 1100 (AEDT) - Wray Buntine (Monash): "Insights into Deep Learning." Download Link. Youtube Link. Slides Link.
  • 14/04/2020 1900 (AEST) - Erica Hopkins (H-ITS) -  Finding a needle in a haystack: The search for strong gravitational lenses Download Link. Youtube Link.
  • 28/04/2020 1000 (AEST) - Cris Sabiu (Yonsei University) - Analysing the cosmic large scale structure with higher order statistics and machine learning. Download Link. Youtube Link.
  • 12/05/2020 1900 (AEST) - James Farr (University College London) - QuasarNET: Quasar Classification in Spectroscopic Surveys. Download Link. Youtube Link.
  • 26/05/2020 1000 (AEST) - Michelle Boyce (Manitoba) - Topological Computational Techniques for source classification and morphology. Download Link. Slides Link. Youtube Link.
  • 09/06/2020 1900 (AEST) - Antonio D'Isanto (H-ITS) - The two worlds of photometric redshift estimation via machine learning: fully automatic vs feature based. Download link. Youtube Link.
  • 23/06/2020 1000 (AEST) - Colin Jacobs (Swinburne) - Probing Neural Networks for science: What is it they are learning? Download Link. Youtube Link.
  • 07/07/2020 1900 (AEST) - Michelle Lochner (African Institute for Mathematical Sciences) - Anomaly Detection with Machine Learning for Astronomical Data. Download Link. Youtube Link.
  • 21/07/2020 1000 (AEST) - No meeting due to EMU International Meeting
  • 04/08/2020 1900 (AEST) - No Meeting
  • 18/08/2020 1000 (AEST) - Shae Brown (University of Iowa) - Classifying Complex Radio Sources and Faraday Spectra with Convolutional Neural Networks. Download Link. Youtube Link.
  • 01/09/2020 1900 (AEST) - No Meeting
  • 15/09/2020 1000 (AEST) - No Meeting
  • 29/09/2020 1900 (AEST) - No Meeting
  • 13/10/2020 1000 (AEDT) - David Parkinson (KASI) - Bayesian Model Averaging: dealing with model ambiguities in a systematic manner. Audio Link. Slides link.
  • 27/10/2020 2000 (AEDT) - No Meeting
  • 10/11/2020 1000 (AEDT) - No Meeting
  • 24/11/2020 2000 (AEDT) - Burger Becker (Stellenbosch University) - Comparing CNN performance on radio galaxy classification. Download Link. YouTube Link
  • 08/12/2020 1000 (AEDT) - Joshua Speagle (University of Toronto) - Dealing with heterogeneous data in photometric redshift predictions. Download Link. Youtube Link.

 

Meetings alternate between two times (time may not be accurate close to the daylight changeover period -  please check your local time against UTC)

  UTC  Sydney (AEDT) Perth (AWST) Paris (CET)  Denver (MST) 
America-friendly Mon. 2300
Tue. 1000
Tue. 0700
Tue. 1200
Mon. 0700
Euro-friendly Tue. 0900
Tue. 2000
Tue. 1700
Tue. 1000
Tue. 0200

 

 

How to join the meeting remotely (Note Zoom address has changed):

 

Potential future talks: 

  • Nic Ralph (Western Sydney University) - Neuromorphic unsupervised tracking of fast transient objects using event-based vision sensors
  • Rui Luo (CSIRO) - Injecting “unexpected” signals into real (or simulated) data sets and then discuss ideas (linked to machine learning) on how to identify those signals

 

Format of Talks (suggestions for speakers)

The length is anything from 30 to 50 mins - you choose. In any remaining time (the meeting is scheduled to last for up to 1 hour) we will have an informal discussion about the topics you raise. I suggest you use a powerpoint/keynote/pdf, and expect people to chip in with questions, or even trigger a discussion, as you go along. I.e. the tone is relaxed and informal. Nobody is going to give you a hard time. Think of it as chatting with your peers about your work. Bear in mind that the audience ranges from data scientists who know little about astronomy to astronomers who know little about machine learning, so try to keep the jargon to a minimum, or explain It if you need to use it.

 

Recordings of Meetings in 2019

See this page

 

Recordings of Meetings in 2018 and earlier

See this page

 
Version:1.0 StartHTML:0000000105 EndHTML:0000038686 StartFragment:0000038405 EndFragment:0000038646 Stellenbosch University Stell

Comments (0)

You don't have permission to comment on this page.