Genetic adaptive system for image understanding and learning research. Phase 1. Final technical report, 1 February-1 August 1989
This report documents the efforts and results of initial phase research on machine learning directed at application for real-time machine vision and automatic target recognition. The particular paradigm pursued is based on genetic algorithms and classifiers modeled on the summation of Mendelian genetic recombination, Darwinian selection, and ecological notions of competition. This machine-learning approach is strongly supported by sound statistical theory. A second thread of research was the development of massively parallel computing hardware based on the Geometric/Arithmetic Parallel Processor (GAPP). This machine has a large number of processors, each one bit wide with a full Arithmetic/Logic Unit (full adder) and with local memory per processor. The basic research hypothesis of the subject effort has been that GAPP contained sufficient hardware capability to provide a substrate for a Classifier and Genetic Algorithm system. The goal has been demonstrated by constructing and running the necessary software on the GAPP, its controller and its host. The resulting fusion of software and hardware is called a Genetic Algorithm/Classifier Engine (GACE) in the same sense as a LISP engine or a data base engine. The resulting quantum jump in performance should open doors both to application and to more interesting and relevant research.
- Research Organization:
- Institute for the Study of Intelligent Systems, Ann Arbor, MI (USA)
- OSTI ID:
- 6995423
- Report Number(s):
- AD-A-214810/4/XAB; ISIS-10037U/89-02C
- Resource Relation:
- Other Information: Original contains color plates: All DTIC and NTIS reproductions will be in black and white
- Country of Publication:
- United States
- Language:
- English
Similar Records
Extreme-Scale Algorithms & Software Resilience (EASIR) Architecture-Aware Algorithms for Scalable Performance and Resilience on Heterogeneous Architectures
The creation of an alternating sequential/parallel Lisp machine
Related Subjects
59 BASIC BIOLOGICAL SCIENCES
ARRAY PROCESSORS
ARTIFICIAL INTELLIGENCE
GENETICS
ALGORITHMS
IMAGE PROCESSING
MAN-MACHINE SYSTEMS
MEMORY DEVICES
PARALLEL PROCESSING
COMPUTER CODES
GEOMETRY
LEARNING
LISP
PROGRESS REPORT
SUBSTRATES
BIOLOGY
DOCUMENT TYPES
MATHEMATICAL LOGIC
MATHEMATICS
PROCESSING
PROGRAMMING
PROGRAMMING LANGUAGES
990200* - Mathematics & Computers
550400 - Genetics