Deep learning for image classification

The aim of this course is to introduce Deep Learning and give insight into its advantages and disadvantages (going beyond the hype!). We will give an overview of the existing techniques and applications, show the differences to traditional approaches, and discuss the limitations of deep learning. As part of the tutorial, we will build a deep learning system from the ground up, and train it.


  • Background on neural nets, history, performance bottlenecks
  • Training deep nets
  • Regularization (dropout)
  • Interpreting weights on a hidden layer

After participating in this course you should be able to

  • Assess if deep learning is suitable for a given problem
  • Implement deep learning systems


Familiarity with Python. But if you know some other programming language well you can pick up Python and the environment in a week.

Good to have

A laptop with a Nvidia GPU and the CUDA compiler installed if you want to run deep learning experiments locally.