Institute of Electrical & Electronic Engineers
In large neural networks, partial connectivity is both biologically plausible and a matter of necessity when targeting a hardware implementation. The authors are using the SpiNNaker neural chip multi-processor to model such networks as a drop-in replacement for the lens network simulator. For the popular MLP network, a theoretical model of the relation between connectivity, network size and gain in the activation function provides a method to set these parameters to near-optimal values. Initial test results show a clear connectivity-gain relation and a benefit to partial connectivity in both networks, with optimal hidden-output connectivity values ranging from 10%-30% depending on the network type.