2018/03/21 by Daniel Fojo, Víctor Campos, Fojo, Daniel +3
Computer Science · #Advanced Neural Network Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.1803.08165
openalex publication_date 2018/03/21 · openalex created_date 2018/03/29 · openalex updated_date 2026/07/28
Adaptive Computation Time for Recurrent Neural Networks (ACT) is one of the most promising architectures for variable computation. ACT adapts to the input sequence by being able to look at each sample more than once, and learn how many times it should do it. In this paper, we compare ACT to Repeat-RNN, a novel architecture based on repeating each sample a fixed number of times. We found surprising results, where Repeat-RNN performs as good as ACT in the selected tasks. Source code in TensorFlow and PyTorch is publicly available at https://imatge-upc.github.io/danifojo-2018-repeatrnn/