Machines d'apprentissage extrême

Définition

XXXXXXXXX

Français

XXXXXXXXX

Anglais

Extreme learning machines

  is a new learning algorithm for the feedforward neural networks with single layer or multiple layers of hidden nodes, where the weights between inputs and hidden nodes are randomly assigned and never updated during training and predicting phases. It uses Moore Penrose generalized inverse to set its weights. ELMs are able to produce acceptable predictive performance and it learn thousands of times more faster than other algorithm and their computational cost is much lower than networks trained by the back propagation algorithm.

Source : medium.com/