RECOG-ORNL
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
- Project Type:
- Closed Source
- Site Accession Number:
- 4343
- Software Type:
- Scientific
- Programming Language(s):
- NESC9967/01: FORTRAN-IV NESC9967/02: FORTRAN-77
- Research Organization:
- OECD Nuclear Energy Agency
- Sponsoring Organization:
- USDOEPrimary Award/Contract Number:
- Code ID:
- 120853
- OSTI ID:
- code-120853
- Country of Origin:
- United States
Similar Records
User's manual for the pattern recognition code RECOG-ORNL. [In FORTRAN IV for IBM 360 (also SIZE, a preprocessor predicting array sizes for RECOG-ORNL, for PDP-10)]
Neural network and letter recognition