Modified Long Short-Term Memory Recurrent Neural Network Architectures

Manish Rana, Shubham Mishra

Abstract: Long Short-Term Memory (LSTM) is a specific recurrent neural network (RNN) architecture that was designed to model temporal sequences and their long-range dependencies more accurately than conventional RNNs. In this paper, we explore LSTM RNN architectures and made some changes for its better performance. LSTM RNNs are more effective than DNNs. Here, we have changed the gates calculation and also have removed some unnecessary features of standard LSTM architecture. This architecture makes more effective use of model parameters than the others considered, converges quickly, and outperforms a deep feed forward neural network having an order of magnitude more parameters.

Keywords: Long Short-Term Memory, LSTM, recurrent neural network, RNN

How to Cite?: Manish Rana, Shubham Mishra, "Modified Long Short-Term Memory Recurrent Neural Network Architectures", Volume 6 Issue 11, November 2017, International Journal of Science and Research (IJSR), Pages: 36-39, https://www.ijsr.net/getabstract.php?paperid=ART20177744, DOI: https://dx.doi.org/10.21275/ART20177744

Download Citation: APA | MLA | BibTeX | EndNote | RefMan