Recurrent neural network pruning using dynamical systems and iterative fine-tuning

Christos Chatzikonstantinou, Dimitrios Konstantinidis, Kosmas Dimitropoulos and Petros Daras.   Network pruning techniques are widely employed to reduce the memory requirements and increase the inference speed of neural networks. This work proposes a novel RNN pruning method that considers the RNN weight matrices as collections of time-evolving signals. Such signals that represent weight vectors can …

Recurrent neural network pruning using dynamical systems and iterative fine-tuning Read More »