Skip to: Site menu | Main content

Written Assignments

Caleb Watson
Building blocks and architecture of neural networks
PDF
Jasper Petschat
Matlab’s Deep Learning Toolbox
PDF
Thomas Lettau
A simple network to recognise handwritten digits
PDF
Daniil Kudrin
How the backpropagation algorithm works
PDF
Denis Gessert
Universality of neural networks
PDF
Markus Heber
Training of deep networks - unstable and vanishing gradients
PDF
Roman Worschech
Deep learning : convolutional networks
PDF

Talks

Talks take place Wednesdays 15:15-16:45, SR 210 (Brüderstraße 16)

First meeting on April 3rd 15:15, SR 210

Matlab installation guide by Jasper Petschat: Installation of MATLAB



Wednesday 17.04.2019, 15.15 Caleb Watson
Building blocks and architecture of neural networks
Slides
Wednesday 08.05.2019, 15.15 Jasper Petschat
Matlab’s Deep Learning Toolbox
Slides Matlab Code
Wednesday 15.05.2019, 15.15 Thomas Lettau
A simple network to recognise handwritten digits
Slides Matlab Code
Wednesday 22.05.2019, 15.15 Daniil Kudrin
How the backpropagation algorithm works
Slides
Wednesday 05.06.2019, 15.15 Heinrich-Gregor Zirnstein
Improving the way neural networks learn - cross-entropy cost function, overfitting and regularization
Notes
Wednesday 19.06.2019, 15.15 Denis Gessert
Universality of neural networks
Slides Animations
Wednesday 26.06.2019, 15.15 Markus Heber
Training of deep networks - unstable and vanishing gradients
Slides Matlab Code
Wednesday 03.07.2019, 15.15 Roman Worschech
Deep learning : convolutional networks
Slides Matlab Code

Course Information

Recommended Reading: Neural Networks and Deep Learning
  Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville
  Matlab Deep Learning Toolbox Documentation
  Matlab Deep Learning Toolbox