Skip RNN swMATH ID: 36445 Software Authors: Victor Campos, Brendan Jou, Xavier Giro-i-Nieto, Jordi Torres, Shih-Fu Chang Description: Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks. Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long term dependencies. In backpropagation through time settings, these issues are tightly coupled with the large, sequential computational graph resulting from unfolding the RNN in time. We introduce the Skip RNN model which extends existing RNN models by learning to skip state updates and shortens the effective size of the computational graph. This model can also be encouraged to perform fewer state updates through a budget constraint. We evaluate the proposed model on various tasks and show how it can reduce the number of required RNN updates while preserving, and sometimes even improving, the performance of the baseline RNN models. Source code is publicly available at https://imatge-upc.github.io/skiprnn-2017-telecombcn/ Homepage: https://imatge-upc.github.io/skiprnn-2017-telecombcn/ Source Code: https://github.com/imatge-upc/skiprnn-2017-telecombcn Dependencies: Python; TensorFlow Keywords: Artificial Intelligence; arXiv_cs.AI; Computer Vision; Pattern Recognition; arXiv_cs.CV; Recurrent Neural Networks; RNNs; Skip State Updates Related Software: IMDB; UCF101; Zoneout; Clockwork RNN; Adam; ImageNet; word2vec Cited in: 0 Publications Standard Articles 1 Publication describing the Software Year Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks Victor Campos, Brendan Jou, Xavier Giro-i-Nieto, Jordi Torres, Shih-Fu Chang 2017