In the ﬁrst course module, we aim to ensure that all students understand the basic concepts and tools in deep learning.
The second course module addresses that learning from data is becoming increasingly important in many diﬀerent engineering ﬁelds. Models for learning often rely heavily on optimization; training a machine is often equivalent solving a speciﬁc optimization problem. These problems are typically of large-scale. In the second module, we will learn how to solve such problems eﬃciently.
The third course module contains research-oriented topics, knowledge of which will be useful in various PhD projects within WASP. This module contains ﬁve diﬀerent topics.
The course is offered in spring 2019 and organized into three different modules:
- Course module 1: 24-25 April, Chalmers
- Course module 2: 20-21 May, Lund university
- Course module 3: 4-5 June, KTH
Course module 1: Deep Learning
April 24-25, Chalmers
Prerequisites: Anyone admitted to WASP-AI should be able to attend this module. However, students with a strong background in Python, machine learning, neural networks and convolutional neural networks are likely to ﬁnd the module very easy, whereas other students will have a harder time, but hopefully also learn a lot from the experience.
Update: A registration form has been sent out to all WASP PhD’s by e-mail. Last day to answer is Monday 11th of February.
Course module 2: Optimization for Learning
May 20-21, Lund University
Prerequisites: Basic knowledge in (convex) optimization and machine learning. The students should know diﬀerent machine learning models that are trained by solving convex problems (linear regression, logistic regression, SVM, empirical risk minimization, etc) as well as deep learning models that are trained via nonconvex optimization.
Course module 3: Deep Learning and GANs
June 4-5, KTH
Prerequisites: From the theoretical point of view, the course assumes general knowledge about machine learning, especially core deep learning methods and optimization as well as basic understanding of probability theory and calculus. Furthermore, for the course practicals, basic-to-intermediate knowledge of python is required. Familiarity with deep networks packages TensorFlow and PyTorch will be advantageous.
To pass the course all modules have to be completed.