Describes developments illustrative of the accomplishments of the learning machine research program at Stanford Research Institute.
Determination and Detection of Features in Patterns
In this paper feature determination as a method of training the first layer of weights in a two layer learning machine (Perceptron)is investigated.
Investigation of a Common Training Procedure for Remote and Rapid Design, Repair and Redesign of Devices
The object of this proposed research program is to investigate the possibility of using one training procedure to rapidly and remotely design, repair, and redesign devices.
Research on Self-Organizing Machines
Submitting a proposal to provide funds for the continuation of work in several important areas of learning-machine research.
Mathematical Techniques of Self-Organizing Systems
This proposal outlines a program of research aimed at the development of a mathematical structure to serve as a means for realizing a useful, economical, self-organizing machine.
Research in 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.
Graphical Data Processing Research Study and Experimental Investigation
We aimed to conduct a research study and experimental investigation of techniques and equipment characteristics suitable for application to graphical data processing for military requirements.
Simulation of Neural Networks by Optical-Photographic Methods
A method of using photographic film and pin-hole optical wiring is proposed here to simulate an electronic data processing machine having many elements operating in parallel.