September 1, 1965

Theoretical and Experimental Investigations in Trainable Pattern-Classifying Systems

Citation

Nilsson, N. J., & Isson, J. N. (1965). Theoretical and Experimental Investigations in Trainable Pattern-Classifying Systems.

Abstract

Motivation is given for the use of various trainable pattern-classifying structures called linear and piecewise linear (PWL) machines. The results of various experiments in training are presented. Two different types of training methods were investigated: mode-seeking and error -correction methods.

↓ Download

Read more from SRI

November 20, 2024

SRI and University of Houston receive $3.6M to develop a microreactor to convert carbon dioxide to methanol using renewable energy

By recycling carbon dioxide into methanol, this science supports U.S. climate goals and helps reduce greenhouse gases.
November 18, 2024

Teaching machines to learn like humans could help autonomous systems deal with unfamiliar environments

SRI is spearheading a way for autonomous systems, such as self-driving vehicles and drones, to effectively operate in evolving and adversarial environments such as war zones.
November 13, 2024

Office of Special Education Programs extends SRI’s funding for the Center for IDEA Early Childhood Data Systems

The U.S. Department of Education issues a third five-year cooperative agreement to SRI to lead The DaSy Center.

Theoretical and Experimental Investigations in Trainable Pattern-Classifying Systems

Abstract

Read more from SRI

SRI and University of Houston receive $3.6M to develop a microreactor to convert carbon dioxide to methanol using renewable energy

Teaching machines to learn like humans could help autonomous systems deal with unfamiliar environments

Office of Special Education Programs extends SRI’s funding for the Center for IDEA Early Childhood Data Systems