id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_skrvzqpikvdw5f7sksbktmh32u	Kyoung-jae Kim	Artificial neural networks with evolutionary instance selection for financial forecasting	2006	8	.pdf	application/pdf	5795	605	61	In this paper, I propose a genetic algorithm (GA) approach to instance selection in artificial neural networks (ANNs) for financial data mining. paper, the GA optimizes simultaneously the connection weights between layers and a selection task for relevant instances. In addition, genetically selected instances shorten the learning time approach is a promising method for instance selection in ANN. Keywords: Instance selection; Genetic algorithms; Artificial neural networks; Financial forecasting selection for the instance-based learning algorithm. there are few studies on instance selection for ANN. bits are instance selection codes for the training data. the selected instances within the training data. Step 0 Initialize the populations (the connection weights between layers and the codes for instance selection). (Fitness function: Average predictive accuracy on the selected instances within the training data) instance selection codes for the training data. accuracy of the selected instances within the training data to patterns of the stock market data from the selected instances	./cache/work_skrvzqpikvdw5f7sksbktmh32u.pdf	./txt/work_skrvzqpikvdw5f7sksbktmh32u.txt