[visionlist] Doctoral Project at TU Berlin: Modularized Visual Understanding for Perception-Action Loops

[Olaf Hellwich]

Technische Universität Berlin invites applications for a PhD position
for the Cluster of Excellence "Science of Intelligence".

Please apply at

https://www.scienceofintelligence.de/call-for-applications/open-positions/doctoral-project-modularized-visual-understanding-for-perception-action-loops/


Visual understanding is a key component of biological and synthetic
intelligent systems. As visual sensors (of any kind) provide
high-dimensional data vectors with structural relationships between
vector elements, such as multi-channel 2D images, the analysis of visual
data unavoidably is a search problem in highly complex spaces. This is
especially true if the visual input has a time component as in the
visual system of an acting agent. Therefore, the goal of this project is
it to develop a modularized and hierarchical temporal vision system for
representation learning as a basis for a closed perception-action loop.
The system is supposed to allow unsupervised learning of task relevant
representations by leveraging the additional information contained in
the time domain and compensating for the low information density in
video streams.


Description of the doctoral project

The goal of this doctoral project is it to develop a modularized and
hierarchical temporal vision system for representation learning as a
basis for a closed perception-action loop. The system is supposed to
leverage the information contained in the time domain of video in
addition to the information known to be present in single images.
Therefore, multiple frames are to be considered together in order to
compensate for the low information density in video streams and allow
unsupervised learning of task relevant representations.

Duties:

- Conducting experimental research in computer vision
- Analysis of video data to generate algorithms for computer vision
- Automated evaluation of behavior
- Modeling of behavior using representation and reinforcement learning
- Interaction within the SCIoI cluster of excellence
- Compilation of the results for presentations, project reports, and
publications


Application procedure

Applications should include: motivation letter, curriculum vitae,
transcripts of records (for both BSc and MSc + doctoral degree if
applicaple), copies of degree certificates (BSc, MSc), abstracts of
Bachelor-, Master-thesis, e.g. doctoral thesis, list of publications and
one selected manuscript (if applicable), two names of qualified persons
who are willing to provide references, and any documents candidates feel
may help us assess their competence.

To ensure equal opportunities between women and men, applications by
women with the required qualifications are explicitly desired.

Qualified individuals with disabilities will be favored. Applications
are also expressly welcomed
from suitably qualified persons seeking to be entered as “gender
diverse” in the public register.

The TU Berlin values the diversity of its members and is committed to
the goals of equal opportunities.

Please send copies only. Original documents will not be returned.


Prerequisites

Applicants must hold a Diploma/Master’s degree in computer science,
engineering, physics or mathematics. The ideal candidate has a
background in computer vision with strong expertise in machine learning.

The successful applicant should have:

- excellent mathematical skills,
- in depth programming skills (C/C++, Python, Matlab),
- very good command of English, both written and spoken,
- strong interest in visual perception and machine learning,
- a keen interest in understanding intelligence,
- the strong communicative skills required for interdisciplinary research,
- a conscientious work approach, flexibility, good time management, and
ability to work in a team

-- 
Prof. Dr.-Ing. Olaf Hellwich
Technische Universität Berlin, Computer Vision @ Remote Sensing
MAR 6-5, Marchstr. 23, D-10587 Berlin, Germany
Tel. +49(0)30/314-22796; http://www.cv.tu-berlin.de