The HAGEN ASIC's internal architecture provides connectivity between four network blocks and thus enables the composition of recurrent, multi layered neural networks. Therefore and due to the underlying network model (Perceptron), several network blocks may function as one single neural network. Via the digital interface of the HAGEN chip it is furthermore possible to not only do this cross linking within one single chip but also to scale it over chip boundaries. This technique brings up high demands on the communication channels between the ASICs: Besides high bandwidth requirements to interface the network blocks the Perceptron model also requires isochronous network communication.
We developed the Distributed HAGEN system to fullfill all of these requirements. Basic operating unit of the system is the evolution module NATHAN, which basically consists of a Xilinx Virtex-II Pro FPGA, directly connected to HAGEN. Using cutting edge FPGA technology, we can exhaust HAGEN's digital bandwidth, have Multi-GigaBit connectivity, and finally have local CPUs and memory to execute the training software HANNEE. The "distributed" ressources of up to 16 NATHAN modules are hosted by a backplane providing the neccessary support infrastructure. Along with being part of the Electronic Vision(s) group's internal research, the Distributed HAGEN system makes up the second deliverable of the SENSEMAKER EU project.