A gentle introduction to deep learning

Chances are that deep learning could help your research, but you haven't quite started doing it yet. If you have some experience with Python, this workshop introduces you to designing deep learning models with Keras. You'll get to play with Feed Forward Neural Networks in an environment that we provide during the exercises. Even though deep learning relies on mathematics, we avoid it. If you know your maths, you'll be able to fill in these blanks and if not you get to focus on how to use deep learning.

Contents

We will discuss:

• train / test / validation data set splits
• learning curves
• learning rates
• weight initialization
• gradient decent optimization methods for deep learning
• regularization
• overfitting
• convolutional layers
• pre-trained networks for image classification
• word embeddings
• models for text classifications

Furthermore:

• the workshop includes lectures and practicals

Make sure you have elementary experience with programming in Python.
Machines are provided during the course, but you can bring your own laptop with Eduroam or other internet access and the Chrome browser. Many other browsers might also work, however note that Microsoft Edge does not. You'll work in Google Colab, we'll send you one or two small assignments to do in advance, to make sure you'll be able to log in and get started right away during the course.