Admission requirements
Bachelor's degree in Astronomy and/or Physics
Fluency in Python and Linuxs
Experience with processing big data sets
Description
During the course students will be introduced to the field of Deep Learning and its possible applications to astronomy. Next, working in small groups, students will apply Deep Learning to some (open) problems.
Topics:
Basics of machine learning: classification, regression, clustering, overfitting, regularization
Multi-layer Perceptron and Backpropagation, Stochastic Gradient Descent, Dropout
Convolutional Networks for image classification
Recurrent Networks for modelling sequential data
Autoencoders for dimensionality reduction and extracting features from data
TensorFlow, Keras and GPU-computing
Course objectives
Learning basics of deep learning and its possible applications in astronomy
Developing practical skills for designing and training deep networks
Demonstration of newly acquired skills by solving some astronomy related problems
Soft skills
In this course, students will be trained in the following behaviour-oriented skills:
Problem solving (recognizing and analyzing problems, solution-oriented thinking)
Analytical skills (analytical thinking, abstraction)
Creativity (resourcefulness, lateral thinking)
Collaboration (extreme programming, joined research)
Timetable
See Schedules Astronomy master 2017-2018
Mode of instruction
Lectures
Practical classes
student's presentation
Assessment method
Project (70%)
Presentations (30%)
Blackboard
Lecture notes, additional readings and assignments will be provided through Blackboard.
For Blackboard access, you need an ULCN account. More information:
Reading list
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton, Deep Learning, Nature 2015.
Deep Learning, Yoshua Bengio, Ian Goodfellow, Aaron Courville, MIT Press (2017); available from: http://www.deeplearningbook.org/
Selected papers from:
Registration
Via uSis. More information about signing up for your classes can be found here. Exchange and Study Abroad students, please see the Prospective students website for information on how to apply.
Contact information
Lecturer:
dr. W. (Wojtek) Kowalczyk
Assistants:dr. M. Cai