Stanford Research Institute proposes a program that will ultimately lead to the development of machines that will perform tasks that are presently considered to require human intelligence.
This report includes the results of a series of experiments to compare the efficiency of training methods using (1, 0) and (+1,-1) representatives for patterns. It also presents a theoretical explanation which deals with a single TLV rather than with a network of TLV’s as used in the experiments.
The main object of this proposed research program is to investigate the hitherto unrealized possibility of using one training procedures as the common means to rapidly and remotely design, repair, and redesign devices.
Submitting a proposal to extend Contract Nonr 3438 (00) to provide continuing funds for studies of: I) Interpolation or function-modelling in multi-variable systems, II) Learning machine structures composed of cascaded adaptive layers.
In response to Rome Air Development Center Purchase Request No. 152083, this proposal outlines a program of research aimed at the development of a mathematical structure sufficiently comprehensive to serve as a means for subsequently realizing a useful, economical, self-organizing machine.
We are submitting a proposal to cover continuing research in the field of self-organizing machines. The four areas of present interest are: Neural Element Development; Integral Geometry Studies; Distributed Memory Studies; Photographic-Optical Simulation of Neural Nets.
Objective: To conduct a research study and experimental investigation of techniques and equipment characteristics suitable for practical application to graphical data processing for military requirements.
