LSTM: A Search Space Odyssey

by   Klaus Greff, et al.

Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful fANOVA framework. In total, we summarize the results of 5400 experimental runs (≈ 15 years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.


page 8

page 9

page 12


Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer

The Long Short-Term Memory (LSTM) layer is an important advancement in t...

Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks

The standard LSTM recurrent neural networks while very powerful in long-...

An Improved Residual LSTM Architecture for Acoustic Modeling

Long Short-Term Memory (LSTM) is the primary recurrent neural networks a...

Slim LSTM networks: LSTM_6 and LSTM_C6

We have shown previously that our parameter-reduced variants of Long Sho...

Empirical Evaluation of A New Approach to Simplifying Long Short-term Memory (LSTM)

The standard LSTM, although it succeeds in the modeling long-range depen...

ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA

Long Short-Term Memory (LSTM) is widely used in speech recognition. In o...

Semi-tied Units for Efficient Gating in LSTM and Highway Networks

Gating is a key technique used for integrating information from multiple...

Code Repositories


Sequence analyzing using Recurrent Neural Networks (RNN) based on Keras

view repo


Playground for some RNN stuff in Torch.

view repo