Lecture Course: Deep Learning for Graphics, Summer Term 2019
Machine Learning can be found in almost all fields of computer science. This course teaches basic concepts of machine learning and how they are applied to computer graphics. This course covers the whole process of developping, training neural nets and also adapting complex models to new datasets. Learning from 3D points aka. point clouds as it is covered in this course, is a current research topic in the field of computer graphics. Students will thus first learn how to solve standard machine learning problems, before applying their know how to 3D data. All practical realizations will be made in Tensorflow, which is also introduced in the course.
We assume previous knowledge in computer science, but not necessarily in machine learning.
In the workshops we provide sample code and introduction to TensorFlow. For each chapter we prepare simple tasks which teach you how to implement the most basic parts of machine learning in TensorFlow using Python.
Goal of the workshop is that you can start writing your own code in order to train nets and adapt to your specific problems / data sets.
You are welcome to bring your own notebook for coding during the workshop. We will use the google colab platform to have enough compute power provided by google cloud servers.
|Introduction||Intro: Tensorflow 2.0 ||Advanced Architectures||Generative Models||Unstructured CNNs|
|Multi Layer Perceptrions||Convolutional Neural Nets||Workshops||Workshops||Visual Architecture Inspection|
Dr Pedro Hermosilla Casajús
When: 26. - 30. August 2019
Where: Ulm University, O27
20 participants, register here.
If possible, bring your notebook for the workshops.