Research Paper | Computer Science & Engineering | India | Volume 6 Issue 11, November 2017
Modified Long Short-Term Memory Recurrent Neural Network Architectures
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
Edition: Volume 6 Issue 11, November 2017,
Pages: 36 - 39
How to Cite this Article?
Manish Rana, Shubham Mishra, "Modified Long Short-Term Memory Recurrent Neural Network Architectures", International Journal of Science and Research (IJSR), Volume 6 Issue 11, November 2017, pp. 36-39, https://www.ijsr.net/get_abstract.php?paper_id=ART20177744
How to Share this Article?
Similar Articles with Keyword 'LSTM'
A Novel Technique for Authorship Verification of Hijacked Online Social Networks User Accounts
Astha Gupta  | Mahesh Parmar
Image Caption Generator Using Convolutional Neural Network Algorithm