[Doctorandos] Curso de Machine Learning en Astronomia

[Secretaría de Ciencia y Técnica]

A toda la comunidad,

les compartimos información sobre el Curso de Machine Learning que el 
Dr. Laerte Sodré (Universidad de São Paulo, Brasil) dictará entre los 
días 28 de noviembre y 7 de diciembre en nuestra Facultad. Este curso 
fue organizado en el marco de la designación del Dr. Sodré como Profesor 
Visitante de la FCAG.

Atentamente,
Secyt-FCAG

-------------------------------------------------------------

Introduction to Machine Learning in Astronomy
La Plata, Nov 28th to Dec 7th, 2022

The objective of this course is to give a general and practical 
introduction to data science in Astronomy, with focus on machine 
learning tools. We want to give some context on statistical techniques 
used by astronomers and present machine learning procedures useful for 
the analysis in astronomy. We plan 4 classes, with one hour of "theory" 
and one hour of applications using Python.

To be approved in this course, after the classes the student will have 
10 days to present a report with an application of ML techniques. All 
students will also make a 5-10 minutes video describing the project and 
results. We will organize a virtual meeting on a date to be determined 
for presentation of the videos and discussion of all projects.

Postdocs as well as PhD and undergraduate students of Astronomy, 
Geophysics and Meteorology are welcome to attend this course. 
Researchers are also welcome to attend but priority will be given to 
postdocs and students.

If you are interested in attending this course, please contact Dr. 
Analía Smith Castelli (asmith en fcaglp.unlp.edu.ar).

Program of the Lectures

Lecture 1: Introduction to Statistics for Data Analysis in Astronomy.
Lab1: introduction to python and Jupyter notebooks descriptive statistics.

Lecture 2: Machine Learning: general concepts.
Lab2: data exploration with non-parametric techniques.

Lecture 3: Regression & Classification.
Lab3: tools for regression and classification; applications on real data 
the workflow of ML.

Lecture 4: Deep Learning.
Lab4: neural networks with the Keras/TensorFlow package and Google Colab.

References
- Statistics, Data Mining, and Machine Learning in Astronomy, Ivezić, 
Connolly, VanderPlas & Gray, 2014 (https://www.astroml.org/)
- An Introduction to Statistical Learning, James, Witten, Hastie & 
Tibishirani, 2021 (https://www.statlearning.com/)
- Deep Learning, Goodfellow, Bengio & Courville, 2016 
(https://www.deeplearningbook.org/)
- Deep Learning with Python, Chollet, 2018 
(https://www.manning.com/books/deep-learning-with-python)
- Modern Statistical Methods for Astronomy: With R Applications , 
Feigelson & Babu, 2012
- Bayesian Methods in Cosmology, Trotta, arXiv:1701.01467, 2017
- The theory that would not die: How Bayes’ Rule Cracked the Enigma 
Code, Hunted Down Russian Submarines, and Emerged Triumphant from Two 
Centuries of
Controversy, Sharon Bertsch Mcgrayne, 2011
- Bayesian Methods for Hackers: Probabilistic Programming and Bayesian 
Inference, Cameron Davidson-Pilon, 2015
- Probabilistic Deep Learning with TensorFlow 2, Imperial College London 
@ www.coursera.com <http://www.coursera.com>
- The Dawes Review 10: The impact of deep learning for the analysis of 
galaxy surveys, M. Huertas-Company & F. Lanusse, arXiv:2210.01813, 2022

---------------
Dra. Analia Smith Castelli
Investigadora Independiente - CONICET
Instituto de Astrofisica de La Plata, UNLP-CONICET
Facultad de Ciencias Astronomicas y Geofisicas, UNLP
Paseo del Bosque s/n, La Plata, Buenos Aires, Argentina (B1900FWA)
email: asmith en fcaglp.unlp.edu.ar
phone: +54 221 4236593 int. 1117
------------ próxima parte ------------
Se ha borrado un adjunto en formato HTML...
URL: <http://fcaglp.fcaglp.unlp.edu.ar/pipermail/doctorandos/attachments/20221102/2aa8a293/attachment.html>