 |
Almost any company that makes products using an
automated production line needs some kind of quality control. Very
often their quality control includes visual inspection. If this
inspection task is to be automated in a machine vision system, one
has to solve the problem of how to implement a human
decision-making process (good part vs. bad part) in software.
Currently, this requires a step-by-step reprogramming or
parametrization of the software, which may last for several months
until satisfying results are obtained. The results of this project
will enable us to use human-machine cooperation to learn
complicated inspection tasks instead of step-by-step improvements
and adaptations of software. The main goal is the development of
machine learning methods to achieve dynamically reconfigurable
systems in production and manufacturing. [more] |
|
Spiking Neurons are a recent model of neurons
which are very promising due to their computational power and their
hardware implementations possibilities. But the question of
training a spiking neural network is still an open research
problem. This project aims at studying on the one hand how to train
spiking neurons with reinforcement learning or supervised learning
and on the other hand how to apply them to control problems for
autonomous robots. It is a collaboration between the PARIS research
group of the UGent and the PMA research group of the K.U.Leuven.
[more] |
Print