eBook XXX Winter School:
summaries, talks, references, and tutorials
This webpage contains the materials needed to follow the lectures given during the school.
It contains a summary with the contents given by each one of the lectures (named as Lectures notes), followed by the recorded talks (Lecture #) and the slides used for them (Lecture slides). References, tutorials, and suggestions for additional reading are also included.
from the Organizers
General overview on the use of machine learning techniques in astronomy
By: Prof. S. George Djorgovski, Caltech, Division of Physics, Mathematics and Astronomy
- Transformation of science driven by computing and information technology.
- From Virtual Observatory to Astroinformatics and beyond.
- Methodology transfer in data science.
Lecture 2: Data visualization
- Basics of data visualization.
- Using color.
- Multidimensional data visualization and Virtual Reality.
- The challenges of transient classification.
- A brief overview of the ML methodology and feature selection.
- Characterizing the light curves.
- Archival data mining in time domain
- Periodicity searches.
- Predictive data mining.
- Automated follow-up decision making.
By: Prof. Mario Juric, University of Washington
This series discusses data challenges and solutions in forthcoming large astronomical surveys. It covers the topic broadly, but with additional focus on Large Synoptic Survey Telescope (LSST) as the largest ground-based survey of the next decade, and the Zwicky Transient Facility (ZTF) the closest time-domain precursor to LSST which is operating today.
Machine Learning: Unsupervised
By: Dr. Dalya Baron, School of Physics and Astronomy, Tel-Aviv University
Lecture 3: Dimensionality reduction algorithms
Lecture 4: Dimensionality reduction algorithms
Tutorials and related materials
Machine Learning: Supervised
By: Prof. Michael Biehl, Bernoulli Institute for Mathematics and Computer Science, University of Groningen
Lecture 1: Introduction
- Supervised learning, clasification, regression.
- Machine learning “vs.” statistical modeling.
Tutorials and extra materials
By: Prof. Marc Huertas-Company, Université Paris-Diderot - Observatoire de Paris; Instituto de Astrofísica de Canarias
- Pereptron, neuron definition
- Layer of neurons, hidden layers
- Activation Functions
- Optimization (gradient descent)
- Convolutions as neurons
- CNNs (pooling, dropout)
- Vanishing Gradient / Batch normalization
- Data Augmentation
- Transfer Learning
- CNN as feature extractor for astronomy
- Optimizing your net: hyper parameter search
- Visualizing CNNs (deconvnets, inceptionism, integrated gradients)
Lecture 4: CNNs as Image Generators
- Variational Auto Encoders
- Generative Adversarial Networks