Grow and Prune Compact, Fast, and Accurate LSTMs

Long short-term memory (LSTM) has been widely used for sequential data modeling. Researchers have increased LSTM depth by stacking LSTM cells to improve performance. This incurs model redundancy, increases run-time delay, and makes the LSTMs more prone to overfitting. To address these problems, we propose a hidden-layer LSTM (H-LSTM) that adds hidden layers to LSTM's original one-level nonlinear control gates. H-LSTM increases accuracy while employing fewer external stacked layers, thus reducing the number of parameters and run-time latency significantly. We employ grow-and-prune (GP) training to iteratively adjust the hidden layers through gradient-based growth and magnitude-based pruning of connections. This learns both the weights and the compact architecture of H-LSTM control gates. We have GP-trained H-LSTMs for image captioning, speech recognition, and neural machine translation applications. For the NeuralTalk architecture on the MSCOCO dataset, our three models reduce the number of parameters by 38.7x [floating-point operations (FLOPs) by 45.5x], run-time latency by 4.5x, and improve the CIDEr-D score by 2.8 percent, respectively. For the DeepSpeech2 architecture on the AN4 dataset, the first model we generated reduces the number of parameters by 19.4x and run-time latency by 37.4 percent. The second model reduces the word error rate (WER) from 12.9 to 8.7 percent. For the encoder-decoder sequence-to-sequence network on the IWSLT 2014 German-English dataset, the first model we generated reduces the number of parameters by 10.8x and run-time latency by 14.2 percent. The second model increases the BLEU score from 30.02 to 30.98. Thus, GP-trained H-LSTMs can be seen to be compact, fast, and accurate.