A general purpose analog neural computer

摘要

The design of a programmable analog neural computer and simulator is described. The machine is intended for real-world real-time computations such as vision, acoustics, or robotics and the development of special-purpose neural nets. The computer is scalable and composed of interconnected switches. It runs entirely in analog mode but connection architecture, synaptic gains, and time constants as well as neuron parameters are set digitally. Each neuron has a limited number of inputs and can be connected to any but not all other neurons. For the implementation of learning algorithms the neuron outputs are multiplexed and converted to digital form. Even at the moderate size of 10/sup 3/ to 10/sup 5/ neurons the computational speed is expected to exceed that of any current digital computer.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>