TY - GEN
T1 - LSTM with working memory
AU - Pulver, Andrew
AU - Lyu, Siwei
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/6/30
Y1 - 2017/6/30
N2 - Previous RNN architectures have largely been superseded by LSTM, or 'Long Short-Term Memory'. Since its introduction, there have been many variations on this simple design. However, it is still widely used and we are not aware of a gated-RNN architecture that outperforms LSTM in a broad sense while still being as simple and efficient. In this paper we propose a modified LSTM-like architecture. Our architecture is still simple and achieves better performance on the tasks that we tested on. We also introduce a new RNN performance benchmark that uses the handwritten digits and stresses several important network capabilities.
AB - Previous RNN architectures have largely been superseded by LSTM, or 'Long Short-Term Memory'. Since its introduction, there have been many variations on this simple design. However, it is still widely used and we are not aware of a gated-RNN architecture that outperforms LSTM in a broad sense while still being as simple and efficient. In this paper we propose a modified LSTM-like architecture. Our architecture is still simple and achieves better performance on the tasks that we tested on. We also introduce a new RNN performance benchmark that uses the handwritten digits and stresses several important network capabilities.
UR - https://www.scopus.com/pages/publications/85031019927
U2 - 10.1109/IJCNN.2017.7965940
DO - 10.1109/IJCNN.2017.7965940
M3 - Conference contribution
AN - SCOPUS:85031019927
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 845
EP - 851
BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 International Joint Conference on Neural Networks, IJCNN 2017
Y2 - 14 May 2017 through 19 May 2017
ER -