External material
Dive into Deep Learning


This course provides a practical introduction to deep learning, including theoretical motivations and how to implement it in practice.  Throughout the course we emphasize efficient implementation, optimization and scalability, e.g. to multiple GPUs and to multiple machines. The entire course is based on Jupyter notebooks to allow students to gain experience quickly.  

Why do we recommend this course?

This is a unique community-based open-source-course in the form of an interactive book. If you are interested on special topics of machine learning (artificial neural network) and ready to dive deep - here you go! 


Which topics will be covered?

  • Multilayer perceptrons 

  • Backpropagation 

  • Automatic differentiation 

  • Stochastic gradient descent 

  • Convolutional networks for image processing, starting from the simple LeNet to more recent architectures such as ResNet for highly accurate models  

  • Sequence models and recurrent networks, such as LSTMs, GRU, and the attention mechanism

What will I achieve?

By the end of the course, you‘ll be able to...

  • understand the principles of nonparametic estimators. 

  • build modern nonparametic estimators.

Which prerequisites do I need to fulfill?

  • Basic knowledge of Python 

  • Algebra 

  • Statistics 

Who is offering this course?

Aston Zhang
Zachary C. Lipton
Mu Li
Alexander J. Smola

Für die Inhalte der Lernangebote sind die Lernangebotserstellenden verantwortlich.

What else do I need to know?

no open license