skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: RECOG-ORNL

Software ·
OSTI ID:1299150

A general-purpose pattern recognition code, is a modification of the RECOG program, written at Lawrence Livermore National Laboratory. RECOG-ORNL contains techniques for preprocessing, analyzing, and displaying data, and for unsupervised and supervised learning. Data preprocessing routines transform the data into useful representations by autocalling, selecting important variables, and/or adding products or transformations of the variables of the data set. Data analysis routines use correlations to evaluate the data and interrelationships among the data. Display routines plot the multidimensional patterns in two dimensions or plot histograms, patterns, or one variable versus another. Unsupervised learning techniques search for classes contained inherently in the data. Supervised learning techniques use known information about some of the data to generate predicted properties for an unknown set.

Short Name / Acronym:
RECOG-ORNL; 002333IBMPC00
Version:
00
Programming Language(s):
Medium: X; OS: NESC9967/01: MVS/XA (IBM 3090)
Research Organization:
OECD Nuclear Energy Agency
Sponsoring Organization:
USDOE
OSTI ID:
1299150
Country of Origin:
United States