Multi-agent systems and Neural networks for automatic target recognition on air images

摘要

Our purose is, in medium term, to detect in air images, characteristic shapes and objects such as airports, industral plants, planes, tanks, trucks, - with great accuracy and low rate of mistakes. However, we also want to value whether the link between nueral networks and multi-agents systems is relevant and effective. If it appears to be really effective, we hope to use this kind of technology in other fields. TGhat would be an easy and coventient way to depict and to ue the agents' knowledge which is distributed and fragmented. After a first phase of preliminary tests to know if agents are able to given relevant information to a neural network, we verify that only a few agents running on an image are enough to inform the network and let it generalize the several multi-agents systems running at the same time on different computers with different images. All those agents send information to a "multi enural networks system" whose job is to identify the shapes detected by the agents. The name we gave to our project is Jarod.