Stanford Research Institute Menlo Park United States
In response to Rome Air Development Center Purchase Request No. 64-707, dated February 3, 1964, this proposal outlines a program of research aimed at developing a Calculus of Networks of Adaptive Elements. During the past three years, important advances have been made in the field of trainable pattern-classifying machines. Particularly productive has been the work on those machines based on networks of adaptive elements. These machines, here called learning machines, often consist of networks of adaptive threshold logic units TLUs. The following development are illustrative of some of the achievements of the learning machine research program at the Stanford Research Institute a development of low-cost, high-speed, electronically adjustable weighting elements b design and construction of a large-scale learning machine, c successful application of learning machine techniques to certain weather prediction problems, d contributions to the theory of the trainability and capacity of a threshold logic unit, e investigations into the mathematical theory of networks of TLUs and f development of techniques for determining basic structural features in patterns.