National Centre of Competence in Research PlanetS
Gesellschaftsstrasse 6 | CH-3012 Bern | Switzerland
  Tel. +41 (0)31 631 32 39
Loading Events

Workshop on Machine Learning

13/02/2019 - 15/02/2019

Machine Learning methods have been around for many years now and their use is growing within the astronomical community. This 3 days workshop will focus on the practical use of supervised and unsupervised Machine Learning techniques on astronomical data, with short theoretical introductions followed by extensive hands-on sessions. The aim of the workshop is to provide astronomers with practical skills they could directly use in their research. The participation requires no prior knowledge of Machine Learning, only some basic knowledge of python.

Subjects

  • Supervised: Deep Learning for transit detection
  • Supervised: from linear regression, through XGBoots to AutoML and SVM
  • Unsupervised: Dimensionality Reduction from PCA to T-SNE

Speakers

Prof Paolo Favaro, Bern University, Switzerland

Paolo Favaro received the Laurea degree (B.Sc.+M.Sc.) from Università di Padova, Italy in 1999, and the M.Sc. and Ph.D. degree in electrical engineering from Washington University in St. Louis in 2003 and 2004 respectively. He was a postdoctoral researcher in the computer science department of the University of California, Los Angeles and subsequently in Cambridge University, UK. Between 2004 and 2006 he worked on medical imaging at Siemens Corporate Research, Princeton, USA. From 2006 to 2011 he was Lecturer and then Reader at Heriot-Watt University and Honorary Fellow at the University of Edinburgh, UK. In 2012 he became full professor at Universität Bern, Switzerland. His research interests are in machine learning, computer vision, computational photography, signal and image processing, estimation theory, inverse problems and variational techniques.

Prof Stéphane Canu, LITIS, INSA, Rouen, France

Stéphane Canu is a Professor of the LITIS research laboratory and of the information technology department, at the National institute of applied science in Rouen (INSA). He has been the dean of the computer engineering department he create in 1998 until 2002 when he was named director of the computing service and facilities unit. In 2004 he join for one sabbatical year the machine learning group at ANU/NICTA (Canberra) with Alex Smola and Bob Williamson.  In the last five years, he has published approximately thirty papers in refereed  conference proceedings or journals in the areas of theory, algorithms and applications  using kernel machines learning algorithm and other flexible regression methods.  His research interests includes deep learning, kernels machines, regularisation, machine learning applied to signal processing, pattern classification, factorisation for recommander systems and learning for context aware applications.

Agenda

Wednesday, 13/02/2019: Deep Learning by Prof. P. Favaro

8:30 Welcome coffee

8:45 – 10:15: Machine Learning introduction

10:15 – 10:30: coffee break

10:30 – 11:30: Deep Learning theory

11:30 – 13:00: Deep Learning practise

13:00 – 14:00: Lunch break

14:00 – 15:00: Deep Learning theory

15:00 – 15:15: coffee break

15:15 – 17:30: Deep Learning practise

Thursday, 14/02/2019: Supervised Learning by Prof. Stéphane Canu

9:00 – 10:30: Using scikit-learn with Astronomical data

10:30 – 10:45: Coffee break

10:45 – 12:00: Linear regression: theory and practise

12:00 – 13:00: XGBoost: theory and practise

13:00 – 14:00: Lunch break

14:00 – 15:00: Automated Machine Learning: theory and practise

15:00 – 15:15: Coffee break

15:15 – 17:30: SVM: theory and practise

Friday, 15/02/2019: Unsupervised Learning by Prof. Stéphane Canu

9:00 – 10:30: PCA: theory and practise

10:30 – 10:45: Coffee break

10:45 – 13:00: PCA – cont.

13:00 – 14:00: Lunch break

14:00 – 16:00: T-SNE: theory and practise

16:00 – 16:15: Coffee break

16:15 – 17:15: “Industrial applications of AI and lessons learned” by Dr Marcin Pietrzyk from Unit8

Practical information

When: 3 days, from 13th to 15th of February 2019

Where: Geneva Observatory

How to get there by public transport: take the train to Versoix, then bus U from Versoix-Gare to Observatoire de Geneve: timetable

Accommodation

A number of rooms are pre-reserved in the Lake Geneva Hotel in Versoix from 12th to 15th February. The price for the single room with breakfast is 157 CHF per night + tourist tax of 3.30 CHF per person per night. During your stay you have free access to the Geneva public transport: buses, trams and boats.

Subscription

In order to subscribe, please fill the form. The subscription deadline is the 10th January 2019.

Due to organisation reasons, the workshop is limited to 30 people. The participants are accepted according to the subscription order.

 

Details

Start:
13/02/2019
End:
15/02/2019

Venue

Geneva Observatory
Chemin des Maillettes, 51
1290 Sauverny,
+ Google Map
Website:
https://www.unige.ch/sciences/astro/