UPLINX-Logo

Machine Learning School

October 9 - 11, 2019
Saarbruecken, Germany
DFKI
UPLINX-MLS-flyer-snip

Flyer

Practical Exercises (Hands-On Sessions)

Practical exercises are currently fully booked! Waiting list available.

(1) Deep Neural Networks for Distracted Driver Detection:

This practical exercise focuses on the application of convolutional neural networks to detect distracted drivers. Participants in this exercise will learn how to program  a Deep Neural Network for image recognition in Keras and will explore different aspects of Neural Networks including noise tolerance, the effect of different hyperparameters, etc. This exercise is aimed at participants familiar with Machine Learning concepts, but who don’t necessarily have practical experience in Deep Learning. Participants should have some programming experience preferably in Python. After completing the exercise, participants will know how to design and train a CNN using Keras, Docker and Jupyter Notebooks.

The number of participants for this practical exercise is limited to 24 (max. 8 groups of 3) due to limited availability of GPUs. No physical computer but only remote access to the GPU will be provided: Participants need to bring their own laptop.

Tutors: Guillermo Reyes, Amr Gomaa
 

(2) Deep Neural Networks for Motion Modeling and Synthesis:

The idea for this practical exercise session is to give access to our motion modelling and synthesis pipeline that makes use of various machine learning techniques such as convolutional neural networks and PCA.  In practical terms, the participants in this exercise session would capture motions, semantically annotate these motions in a semi-automated manner, possibly cut motions into motion primitives, and produce motion models for these motion primitives. Depending on whether the approach chosen by the participants allows for it, the participants can also decorate the motion models with different motion styles (male, female, old, child, bold etc.). The resulting motions can then be visualized in a predefined environment.

The number of participants for this practical exercise is limited to 24 (max. 8 groups of 3) due to limited availability of GPUs. No physical computer but only remote access to the GPU will be provided: Participants need to bring their own laptop

Tutors: Klaus Fischer, Janis Sprenger, Somayeh Hosseini, Noshaba Cheema, Han Du, Erik Herrmann

Impressum