The Master of Science in Engineering – MSE of HES-SO is launching a new master course on Deep Learning this autumn semester in Zurich. The institute of Complex Systems – iCoSys has been selected through Prof. Jean Hennebert to lead this new module, together with Prof Martin Melchior from FHNW. The teaching team will also include our collaborators Dr. Christophe Gisler and Julien Esseiva.
The learning objectives are:
- have a thorough understanding of neural network architectures including convolutional and recurrent networks.
- know loss functions (e.g. categorical cross entropy) that provide the optimization objective during training.
- understand the principles of back propagation.
- know the benefits of depths and representation learning.
- have an overview of open research questions.
- develop the ability to decide whether Deep Learning is suitable for a given task.
- gain the ability to build and train neural network models in a Deep Learning Framework such as TensorFlow.
iCoSys is also involved in the following master-level teaching: Machine Learning (Lausanne, autumn semester), Parallel computation and algorithms (Lausanne, spring semester), Advanced Software Architecture and Design (Lausanne, spring semester), Development methodologies and Architectures (Lausanne , spring semester), Multicore Concurrent Programming (Lausanne, spring semester).