Gating Revisited: Deep Multi-layer RNNs That Can Be Trained

25 Nov 2019  ·  Mehmet Ozgur Turkoglu, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler ·

We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients. Stacking recurrent units into deep architectures suffers from two major limitations: (i) many recurrent cells (e.g., LSTMs) are costly in terms of parameters and computation resources; and (ii) deep RNNs are prone to vanishing or exploding gradients during training. We investigate the training of multi-layer RNNs and examine the magnitude of the gradients as they propagate through the network in the "vertical" direction. We show that, depending on the structure of the basic recurrent unit, the gradients are systematically attenuated or amplified. Based on our analysis we design a new type of gated cell that better preserves gradient magnitude. We validate our design on a large number of sequence modelling tasks and demonstrate that the proposed STAR cell allows to build and train deeper recurrent architectures, ultimately leading to improved performance while being computationally more efficient.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition Jester convSTAR Val 92.7 # 9
Language Modelling Penn Treebank (Character Level) STAR Bit per Character (BPC) 1.30 # 16
Sequential Image Classification Sequential MNIST STAR Unpermuted Accuracy 99.4% # 6