id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_5c6x6vtjqrg2jmbpbikwekbpta	Daniel Mateos-García	An evolutionary voting for k -nearest neighbours	2016	6	.pdf	application/pdf	5740	867	66	This work presents an evolutionary approach to modify the voting system of the k-nearest neighbours (kNN) rule we called Our approach results in a real-valued vector which provides the optimal relative con-tribution of the k-nearest The main goal of a weighting system lies in the optimization (comonly by metaheuristics) of a set of weights in the training step to obain the highest accuracy but trying not to overfit the resulting model. hey considered a weight by feature and instance on training data reulting in a non-viable number of parameters in the learning process. possible better suitability of evolutionary computation for the optimization of the neighbours weights. the elements of the two versions of the evolutionary algorithm designed to weight the vote system of the kNN. he instances from TR, the fitness function was based on a crossalidation error rate by using kNN and the weighted voting system. weight features or instances but the influence of each of the k nearest neighbours.	./cache/work_5c6x6vtjqrg2jmbpbikwekbpta.pdf	./txt/work_5c6x6vtjqrg2jmbpbikwekbpta.txt