Stellenangebot: MASTER THESIS: RESONATOR NETWORK FOR NEUROMORPHIC VISION (M/F/D)
fortiss GmbH
Guerickestraße 25, 80805 München Vollzeit Keine Angabe
MASTER THESIS: RESONATOR NETWORK FOR NEUROMORPHIC VISION (M/F/D)
Who are we?
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:
Neuromorphic vision, through the use of event-based cameras, is paving the way to low-energy, low-latency and fast vision algorithms for robotics and autonomous devices. We at fortiss, research and develop vision algorithms based on spiking neural network and running on neuromorphic hardware and apply them to gesture recognition, robotic arm control or drone-based surveillance. Our research topics include attention mechanisms, spiking convolutional networks, online learning, few shots learning, spiking reinforcement learning, simulated and real neurorobotics, spiking robotic control and more.
In the Neuromorphic Computing department, we propose a
Master Thesis in Neuromorphic Vision
__________
The background:
Neuromorphic vision, through the use of event-based cameras, is paving the way to low-energy, low-latency and fast vision algorithms for robotics and autonomous devices. We at fortiss, research and develop vision algorithms based on spiking neural network and running on neuromorphic hardware and apply them to gesture recognition, robotic arm control or drone-based surveillance. Our research topics include attention mechanisms, spiking convolutional networks, online learning, few shots learning, spiking reinforcement learning, simulated and real neurorobotics, spiking robotic control and more.
Ihre Aufgaben
You will explore the use of spiking resonator networks to solve the problem of visual object identification. This work will base on existing simulated and real implementations of classic algorithmic object identification from a camera mounted on a drone, a project run in collaboration with a major industrial player. We expect resonator networks to solve the problem of noise filtering in the visual scene. Your work will be both theoretical and applied to the drone use case and the Intel Loihi neuromorphic chip and will certainly lead to a scientific publication.
Ihr Profil
- 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.)
- Preliminary knowledge of Neuromorphic (spiking) networks is an asset
Wir bieten
- Work in partnership with a world leading company 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_RN_2023
Contact : Axel von Arnim
Start: March 2023
Job-ID: NC_MS_RN_2023
Contact : Axel von Arnim
Start: March 2023
- Ralf Kohlenhuber
- Human Resources Administrator