A multichip analog neural network
Jan Van der Spiegel, Paul Müeller, V. Agami, P.M. Aziz, David Blackman, P. Chance, A. Choudhury, Christopher Donham, Ralph Etienne‐Cummings, L. Jones, J. Kim, Peter R. Kinget, Mike Massa, Werner Koch, J. Xin · 2002
A multichip, programmable analog neural network for real-time dynamic computations is described. The network's interconnection structure, the neuron characteristics, synaptic connections, and synaptic time constant are modifiable. The chips are designed to allow a modular and expandable gross architecture that can be adjusted to the complexity of the task. The network operates fully analog in real time. However, a digital host is used to set the network parameters and monitor the neuron outputs. A prototype neural computer consisting of 72 neurons has been assembled and tested. The network has been successfully configured for several applications and found to have a performance that is equivalent to a digital machine of 10/sup 11/ FLOPS.>