Using genetic algorithms to improve pattern classification performance
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms for Feature Selection for Counterpropagation Networks
Genetic Algorithms for Feature Selection for Counterpropagation Networks
On growing better decision trees from data
On growing better decision trees from data
Using learning to facilitate the evolution of features for recognizing visual concepts
Evolutionary Computation
PathMiner: a web-based tool for computer-assisted diagnostics in pathology
IEEE Transactions on Information Technology in Biomedicine
| Hi-index | 0.00 |
We are investigating the role of high performance computing for supportof a comprehensive pathology image atlas. The primary computing component isa database access mechanism providing retrieval by content based imagematching (CBIR) along with traditional term based queries. Anorganization based on information theoretic and Bayesian principles usingdecision trees and signature files is being developed. The essential role ofHPC is the discovery, selection, and optimization of medically useful imagefeature sets via genetic algorithm and simulated annealing methods. Thispaper outlines the problem area along with aspects of the underlyingtheoretical basis and distinguishing computing characteristics. Efficiencyof key portions of the computations can be greatly improved by usingparallelism within the computer word length using bit counting instructionsto implement voting and multimedia style instruction sets for low levelimage processing.