This paper reports on the design issues and subsequent performance of a soft intellectual property (IP) core implementation of a self-organizing neural network. The design is a development of a previous 0.65-/spl mu/m single silicon chip providing an array of 256 neurons, where each neuron stores a 16 element reference vector. Migrating the design to a soft… (More)
COBRA is a behavioral high level synthesis tool for datapath dominated applications. It uses a regular architecture which has been previously shown to significantly reduce the area of synthe-sised datapaths and integrates the traditional scheduling, allocation and binding tasks into one global optimisation. Optimisation is performed using simulated… (More)
Acknowledgements We are grateful to John Ockendon for introducing us to this problem. We also thank Björn Stinner and Charlie Elliott for setting up the modelling course, and also Gideon Simpson for his help.