MASTER THESIS: ATTENTION MECHANISM IN NEUROMORPHIC VISION (M/F/D)

fortiss is the research institute of the Free State of Bavaria for software-intensive systems and services with headquarters in Munich. The institute currently employs around 120 employees, who collaborate on research, development and transfer projects with universities and technology companies in Bavaria, Germany and Europe. Research is focused on state of the art methods, techniques and tools of software development, systems & service engineering and their application to reliable, secure cyber-physical systems, such as the Internet of Things (IoT). fortiss has the legal structure of a non-profit limited liability company (GmbH).

In the Neuromorphic Computing department, we propose a

Master Thesis in Neuromorphic Vision

__________
The background:


When looking out at the world, your eyes continuously pick up on “interesting” objects, colours, movements, etc. This measure is known as “saliency”. The attention mechanism through which the brain decision on what is salient is not yet fully understood. In classical machine learning systems, deep convolutional neural networks have been shown to approximate this behaviour by identifying certain patterns or known objects. However, in Neuromorphic (biological event-based) vision, the problem has no agreed upon solution.

__________
Your topic:


We have been exploring biological saliency with a robotic arm carrying a Neuromorphic camera. The arm needs to choose what to explore based on principles of biological saliency. The goal of the thesis would be to explore different algorithms, implemented on Neuromorphic hardware, to achieve reasonable visual attention mechanisms and subsequent object classification. This would be compared to human attention mechanisms, as well as classical ML vision systems.

__________
Your profile:
  • Bachelor degree in computer science, electronics, machine vision or software engineering and an excellent track record in your current master’s studies
  • Good skills with software development (Python; c++ is an asset)
  • Strong experience with machine vision (state-of-the-art CNN, deep learning, etc.)
  • Experience with robotics is an asset
  • Preliminary knowledge of Neuromorphic (spiking) architectures is an asset
__________
Our offer:
  • Work in partnership with a world leading companies in computer technology
  • Central Munich, high and modern premises with 360° view on Munich and the Alps
  • Access to cutting edge robotics and neuromorphic hardware
  • Enjoyable working atmosphere
__________
Did we catch your interest?

 
Please submit your application with a cover letter, a detailed CV, and a current transcript of records.

Job-ID: NC-MS-02-2022
Start: March 2023
Contact: Evan Eames