A Fresh Take on Neural Network Pruning from the Angle of Graph Theory

Model pruning is arguably one of the oldest methods of deep neural networks (DNN) model size reduction that dates to the 90s, and quite stunningly, is still a very active area of research in the AI community. Pruning in a nutshell, creates sparsely connected DNNs that intend to retain model performance as the original dense model.

Ce contenu a été publié dans Non classé. Vous pouvez le mettre en favoris avec ce permalien.