A Survey on Neural Networks Using Memory Component


KIPS Transactions on Software and Data Engineering, Vol. 7, No. 8, pp. 307-324, Aug. 2018
10.3745/KTSDE.2018.7.8.307,   PDF Download:
Keywords: Recurrent Neural Networks, Memory-Augmented Neural Networks, Memory Component, Memory Networks, Neural Turing Machines, Stack-Augmented Neural Networks
Abstract

Recently, recurrent neural networks have been attracting attention in solving prediction problem of sequential data through structure considering time dependency. However, as the time step of sequential data increases, the problem of the gradient vanishing is occurred. Long short-term memory models have been proposed to solve this problem, but there is a limit to storing a lot of data and preserving it for a long time. Therefore, research on memory-augmented neural network (MANN), which is a learning model using recurrent neural networks and memory elements, has been actively conducted. In this paper, we describe the structure and characteristics of MANN models that emerged as a hot topic in deep learning field and present the latest techniques and future research that utilize MANN.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
J. Lee, J. Park, J. Kim, J. Kim, H. Roh, S. Park, "A Survey on Neural Networks Using Memory Component," KIPS Transactions on Software and Data Engineering, vol. 7, no. 8, pp. 307-324, 2018. DOI: 10.3745/KTSDE.2018.7.8.307.

[ACM Style]
Jihwan Lee, Jinuk Park, Jaehyung Kim, Jaein Kim, Hongchan Roh, and Sanghyun Park. 2018. A Survey on Neural Networks Using Memory Component. KIPS Transactions on Software and Data Engineering, 7, 8, (2018), 307-324. DOI: 10.3745/KTSDE.2018.7.8.307.