Commune · Savoirs

Batch normalization

Normalization technique used to make training faster and more stable by adjusting the inputs to each layer, recentering them around zero and rescaling them to a standard size

Texte en anglais

In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable by adjusting the inputs to each layer—re-centering them around zero and re-scaling them to a standard size. It was introduced by Sergey Ioffe and Christian Szegedy in 2015.

Sur Wikipédia

Texte en anglais Pas encore d'article dans ta langue : extrait en anglais.

In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable by adjusting the inputs to each layer—re-centering them around zero and re-scaling them to a standard size. It was introduced by Sergey Ioffe and Christian Szegedy in 2015. Experts still debate why batch normalization works so well. It was initially thought to tackle internal covariate shift, a problem where parameter initialization and changes in the distribution of the inputs of each layer affect the learning rate of the network. However, newer research suggests it does not fix this shift but instead smooths the objective function—a mathematical guide the network follows to improve—enhancing performance. In very deep networks, batch normalization can initially cause a severe gradient explosion—where updates to the network grow uncontrollably large—but this is managed with shortcuts called skip connections in residual networks. Another theory is that batch normalization adjusts data by handling its size and path separately, speeding up training.

Texte : Wikipédia en anglais, CC BY-SA 4.0. ·

Cartes voisines

Ouvrir

…

Touche pour fermer

Confirmation