DeMaMech:
EU-Japan Collaboration in Higher Education Student Exchange Program
Offer of
Research Topic (1 or 2 students)
|
Offer from |
University |
Katholieke Universiteit
Leuven |
|
Faculty/Department/Institute |
Faculty of Engineering
Science Department of
Mechanical Engineering |
|
|
Group Name |
Production engineering,
Machine design and Automation (PMA) |
|
|
Research Theme |
Spiking Neural
Networks and Robotic applications |
|
|
Brief Explanation |
Recently, new neural
models have been investigated that are much more closely coupled with the
binary computations of digital computation and that are even more tightly
linked to the brainÕs operation than classical neural models. These "spiking neural
models" only use bits for the communication between neurons. The neurons
themselves are simply weighted leaking integrators that can fire and that can
be reset as soon as a threshold value is reached. Because the communication
between network nodes now is handled by spikes instead of by floating point
values, we should explore ways of representing the mostly analogue
information from the surroundings into spikes. Several coding techniques are
possible. Recently, Floriano et al. showed that hardware spiking neural
networks are quite useful for autonomous robotics and that they are actually
better suited for the task than classical neural networks. However, very simple neuron models
are used, as well as a global training algorithm (a genetic algorithm). This
is mostly unwanted. The research area of spiking neural networks is still in
full development, especially in Europe. Exciting research topic. |
|
|
Research Steps |
Depending on the
preference of the candidate(s), this subject can either be: (1)
theoretical: study of representation / approximation issues (2)
simulation oriented: enhancement of existing simulators (3)
application oriented: applications to obstacle avoidance and other
robot skills. |
|
|
Period |
5 months, or a 10-month
project (adding real robotic experiments) |
|
|
Necessary Background,
Knowledge, Skills |
Computer programming
skills (C++, also MATLAB if possible). Neural Networks |
|
|
Further Information |
||
|
Contact Person |
Prof.
Marnix Nuttin http://people.mech.kuleuven.ac.be/~mnuttin/ Prof.
Hendrik Van Brussel |
|