Deep Learning Applied to Machine Vision Tasks (free)

Neural networks and deep learning are key to qualitative improvements in many computer vision tasks like object detection, segmentation, and recognition, as well as scene understanding, content-based filtering, and more. This tutorial will utilise the new deep neural network framework in Mathematica to introduce the basic concepts.

In this workshop, we will not go as far as developing a self-driving car from a set of input video streams. However we will demonstrate the practice of the new neural networks capabilities in the Wolfram language by walking through several modern applications such as image quality assessment, or action recognition.

If time allows, we conclude with some exercises.


2 October 2017, 11.00-16.30 Amsterdam




Dr. Markus van Almsick

For over twenty years, Dr. Markus van Almsick has been a consultant for Wolfram Research, maker of Mathematica. He studied theoretical physics at the Technische Universität in Munich and at the University of Illinois, as well as biomedical image analysis at the Technische Universiteit Eindhoven. For the last six year he has been helping to extend the scope of Mathematica in image and signal processing.

All Mathematica 11 events:
2 October 2017 Deep Learning Applied to Machine Vision Tasks (free) 11.00-16.30 Amsterdam subscribe
3 October 2017 Bayes in Action 10.00-17.00 Amsterdam subscribe
8 November 2017 Mathematica Basic Principles I (free) 10.00-17.00 Amsterdam subscribe
9 November 2017 Mathematica Basic Principles II, includes pattern matching (free) 10.00-17.00 Amsterdam subscribe
15 November 2017 Programming with Mathematica (free) 10.00-17.00 Amsterdam subscribe
22 November 2017 Interactivity in Mathematica
an advanced course for constructing more fine tuned interactive output (free)
10.00-17.00 Amsterdam subscribe