<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">Hi all,<div class=""><br class=""></div><div class="">This is a kind reminder about Mike Walmsley’s seminar <b class="">in 40 minutes</b> in <b class="">FC61 </b>and on Zoom.</div><div class="">We hope to see many of you there!</div><div class=""><br class=""></div><div class="">Eliot and Kris</div><div class=""><div><br class=""><blockquote type="cite" class=""><div class="">On 19 Sep 2022, at 13:22, Eliot Ayache <<a href="mailto:eliot.ayache@astro.su.se" class="">eliot.ayache@astro.su.se</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><meta http-equiv="Content-Type" content="text/html; charset=utf-8" class=""><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class="">The next SU astronomy departmental seminar will take place on <b class="">Friday September 23rd at 10:30</b> in room <b class="">FC 61</b> (AlbaNova building, 6th floor) and on zoom.</div><br class=""><div class="">————————————————————————————————————————————————————————————————<br class=""><br class=""><b class="">Speaker: Mike Walmsley - University of Manchester</b></div><div class=""><b class="">Title: Galaxy Zoo in the Deep Learning Era</b></div><div class=""><br class="">Abstract: <br class="">Deep learning is fundamental to Galaxy Zoo’s latest morphology catalogs. In this talk, I explore how we train accurate and reliable models on our volunteer labels, and consider the consequences and opportunities of such models.<br class="">One obvious consequence is scale. We will shortly release detailed morphological classifications for 1.4 million nearby galaxies in the DESI Legacy Surveys - a catalog which would have been impossible with volunteers alone. But the truly new opportunity is using the models to create your own catalogs. Having already learned to answer every GZ question at once, our models are easy to adapt to new surveys and new questions. We recently exploited this to create new (and order-of-magnitude larger) catalogs of mergers in HST and ringed galaxies in DECaLS. You can answer your own morphology questions with our public <a href="https://github.com/mwalmsley/zoobot" class="">code and models</a>.<br class="">Finally, we describe our very latest work on simultaneously learning from labelled and unlabelled galaxy images. Such approaches are ideally suited to Euclid and Rubin because they allow us to leverage both the millions of human labels collected over the last decade and the raw scale of unlabelled images these new surveys will produce.</div><div class=""><br class="">————————————————————————————————————————————————————————————————</div><div class=""><br class=""></div><div class=""><br class="">We look forward to seeing many of you there. Thanks!<br class=""><br class="">Eliot and Kris</div><div class=""><br class=""></div><div class=""><br class="">Topic: Astronomy Department Seminar Mike Walmsley<br class="">Time: Sept 23rd, 2022 10:30 AM Stockholm<br class=""><br class="">Join Zoom Meeting:<br class=""><a href="https://stockholmuniversity.zoom.us/s/61002076352" class="">https://stockholmuniversity.zoom.us/s/61002076352</a></div><div class=""><br class="">Meeting ID: 610 0207 6352</div></div></div></blockquote></div><br class=""></div></body></html>