No account yet ?

In machine learning, the k nearest neighbor method is a supervised learning method.

Abbreviated k-NN or KNN.

There is a learning database made up of N “input-output” pairs.

To estimate the output associated with a new input x, this method consists in taking into account the k training samples whose input is closest to the new input x, according to a distance to be defined.

Since this algorithm is distance-based, normalization can improve its accuracy.

In the classification, we will retain the class most represented among the k outputs associated with the k inputs closest to the new input x.

In pattern recognition, the k-nearest neighbors algorithm is a nonparametric method used for classification and regression.