Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)
Yuzo Hirai
An asynchronous PDM (Pulse-Density-Modulating) digital neural network system has been developed in our laboratory. It consists of one thousand neurons that are physically interconnected via one million 7-bit synapses. It can solve one thousand simultaneous nonlinear first-order differential equations in a fully parallel and continuous fashion. The performance of this system was measured by a winner-take-all network with one thousand neurons. Although the magnitude of the input and network parameters were identi(cid:173) cal for each competing neuron, one of them won in 6 milliseconds. This processing speed amounts to 360 billion connections per sec(cid:173) ond. A broad range of neural networks including spatiotemporal filtering, feedforward, and feedback networks can be run by loading appropriate network parameters from a host system.