Big Data, Machine Learning and Astrophysical Data


course ID

Lecturer

CFU

4

Length

14 Weeks

Semester DD

Second


Course details

This introductory course in covers a wide range of methods and applications of Machine Learning in Astrophysics.

What is Machine Learning? What problems does it try to solve? What are the main categories and fundamental concepts of Machine Learning systems?
Learning by fitting a model to data. Optimizing a cost function.
Handling, cleaning, and preparing data.
Selecting a model and tuning hyperparameters using cross-validation.
The main challenges of Machine Learning.
Reducing the dimensionality of the training data to fight the curse of dimensionality.
The most common learning algorithms: Linear and Polynomial Regression, Logistic Regression, k-Nearest Neighbors, Support Vector Machines, Decision Trees, Random Forests, and Ensemble methods.

The lessons are accompanied with plenty of laboratory hours. In the lab, students learn to program in Python and write their own routines to apply on astrophysical datasets the concepts introduced in the lessons.

Objectives

LEARNING OUTCOMES: The course focuses on advanced data analysis, dealing Big Data and Machine Learning approaches on Astrophysical datasets. The course also aims to extend previous computer skills by thoroughly addressing Object-Oriented programming in Python.
KNOWLEDGE AND UNDERSTANDING: Understanding of numerical techniques for data analysis. - Good knowledge of the state of the art about the use of Machine Learning in the astrophysics field.
APPLYING KNOWLEDGE AND UNDERSTANDING: Understanding the limits of the numerical approaches. - Ability to unassistedly analyze astrophysical data-sets through numerical methods.
MAKING JUDGEMENTS: Ability to perform bibliographic research on Machine Learning approaches in Astrophysics, selecting interesting materials and evaluating the main results. Ability to understand which is the best approach to solve a numerical problem.
COMMUNICATION SKILLS: Ability to present and organize the exposition of a specialized topic of in-depth analysis of astrophysical data analysis.- Proficiency in the Python language to allow advanced use of the most common astrophysics tools and libraries.
LEARNING SKILLS: To be able to approach new fields through independent study.