Publications
-
Engineering Change to Contract AF 30(602)-4147 for Application of Intelligent Automata to Reconnaissance
Engineering Change to Contract AF 30(602)-4147
-
A Plan for a Unified Program of Research in Artificial Intelligence at SRI
The AI research program described here has as its long term, unifying goal the task of building intelligent machines to perform useful tasks.
-
Research on Intelligent Question-Answering Systems
This report describes progress toward an "intelligent question-answering system"-a system that can accept facts, retrieve items from memory, and perform logical deductions necessary to answer questions.
-
Survey of Artificial Intelligence
The end product of the proposed continuation would be a report or reports in which the major techniques and subject matter of Artificial Intelligence are presented and explained in a…
-
Advanced Pattern Recognition Techniques
SRI proposes a research study and experimental investigation of computer-aided methods for the recognition of human faces from photographs.
-
Notes on Classification Capacities
Capacities for single element networks and low dimensional multi-element networks are found, and bounds on capacities are discussed for general networks.
-
Theoretical and Experimental Investigations in Trainable Pattern-Classifying Systems
Motivation is given for the use of various trainable pattern-classifying structures called linear and piecewise linear (PWL) machines.
-
Linear Separability of Signal Space as a Basis for Adaptive Mechanisms
This report reviews the research results of the program entitled "Linear Separability of Signal Space as a Basis for Adaptive Mechanisms".
-
Research in Intelligent Automata (Phase 1)
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.
-
Calculus of Networks of Adaptive Elements
Describes developments illustrative of the accomplishments of the learning machine research program at Stanford Research Institute.
-
Classification and Generalization Capabilities of Linear Threshold Units
This report represents work in progress on properties of linear threshold functions.
-
An Experimental Comparison of Three Learning Machine Training Rules
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.