Introduction to Deep Learning
This course is aimed at researchers and students in academia who are interested in incorporating Deep Learning concepts into their research.
The course will be in held English.
The workshop is free of charge. Participants organize their own refreshments during breaks.
The registration is limited to 20 participants.
Attention! The course is already full. We will organize a similar course in the near future.
Content
This course will introduce the basic concepts of Deep Learning. We will discuss the methods behind neural networks and how to use them set up non-linear models for solving e.g. classification tasks. The basic ideas involved in the process of training neural nets (backpropagation, minimization of loss functions by optimization methods) are treated. We will cover simple deep learning models (with very few fully connected layers) as well as more advanced models such as convolutional neural networks. We shall further focus on the model evaluation and how to effectively train the model. In the hands-on session participants will train their own neural network using the Keras API of TensorFlow.
Target group and requirements
The course is targeted at beginners with no or little knowledge of Deep Learning.
A basic Python knowlege will be of advantage.
Participants are expected to bring their own laptop with with installations (see link section) of
- Python (we suggest using the Anaconda Distribution),
- TensorFlow (either version 1.14 or 2.0 will work for the hands-on tasks),
- scikit-learn.
GPU support is not required for the hands-on part, we will demonstrate GPU usage on an HPC cluster.
As backup solution, participants can bring their laptop with either Linux/MacOS or Windows with MobaXterm installed (see download section for instructions). In this case a WiFi connection with Eduroam is necessary.
