Deep Learning
In the last ten years there has been a revolution in the field of 
Artificial Intelligence, mainly as the result of the revival of an approach called "Deep Learning". Deep Learning is the subfield of Machine Learning which is based
on Artificial Neural Networks with many "layers".

The Deep-Learning course discusses the main ideas and techniques of Deep Learning and explains the practical implementation of Deep Learning algorithms using Python & Keras in detail. The programming part in this course is about 50% of the time. At the end of the course participants will be able to program state of the art algorithms in computer vision with a few lines of code.

The course assumes familiarity with core Python. It is advantageous to have basic knowledge of Linear Algebra, Calculus, and Probability Theory.  The topics covered are:

  • Design of Artificial Neural Networks (ANNs) and how they work.
    - Properties of the main activation functions.
    - When to apply the different kinds of neuron.
    - Which loss function is applicable when.
    - Various optimizers for the training of a model and their properties.
  • Keras
    - The Sequential Model.
    - The functional API in order to program arbitrary net architectures.
  • Construction & Training of neural networks (with Keras, using the TensorFlow backend)
  • TensorBoard. Inspecting the progress in a model training.
  • Convolutional Neural Networks (CNNs)
  • Using pretrained models and adapting them to new problems.
  • Applications of CNNs to Computer Vision Tasks (with Keras)
  • Combining Keras with Scikit-Learn to optimize model parameters and to visualize the model quality.
  • Selected topics from general Machine Learning, including a very gentle introduction to Feature/Representation Learning and to Generalization Theory.

 The standard course duration is 2 days. On request, this course can be combined with one of the other courses  with a duration between 2 and 5 days. Very popular is the combination with the Scikit-Learn-course.
If you are interested in this course, please send us a message, since we plan courses dynamically on demand.