Abstract
The present invention relates to a method for pruning a neural network comprising a plurality of neurons, said method comprising: an initialization phase, wherein input information is fetched comprising at least parameters $({w_{ni},b_{ni}})$ related to said neural network and a dataset (D) representative of a task that said neural network has to deal with, wherein said parameters $({w_{ni},b_{ni}})$ comprising a weights vector (w_{ni}) and/or a bias (b_{ni}) related to at least one neuron of said plurality of neurons; a regularization phase, wherein said neural network is trained according to a training algorithm by using said dataset (D); a thresholding phase, wherein an element $(w_{nij})$ of said weights vector $(w_{ni})$ is put at zero when its absolute value is below a given threshold (T).
Marco Grangetto
Full Professor
