Abstract
The predominant models used to analyze sequential data today are recurrent neural networks, specifically Long-Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, which utilize a temporal value known as the hidden state. These recurrent neural networks process sequential data by storing and modifying a hidden state through the use of mathematical functions known as gates. However, these networks hold many flaws such as limited temporal vision, insufficient memory capacity, and ineffective training times. In response, we propose a simple architecture, the Gated Memory Unit, which utilizes a new element, the hidden stack, a data stack implementation of the hidden state, as well as novel gates. This, along with a parameterized bounded activation function (PBA), allows the Gated Memory Unit (GMU) to outperform existing recurrent models effectively and efficiently. Trials on three datasets were used to display the new architecture’s superior performance and reduced training time as well as the utility of the novel hidden stack compared to existing recurrent networks. On data which measures the daily death rate of SARS-Cov-2, the GMU was able to reduce losses to half that of comparable models and did so in nearly half the training time. Additionally, through the use of a generated spiking dataset, the GMU depicted its ability to use its hidden stack to store information past directly observable time steps. We prove that the Gated Memory Unit performs well on a variety of tasks and can outperform existing recurrent architectures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bingham, G., Miikkulainen, R.: Discovering parametric activation functions. Neural Netw. 148, 48–65 (2022)
Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches (2014). https://doi.org/10.48550/ARXIV.1409.1259
Cho, K., et al.: Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Association for Computational Linguistics (2014). https://doi.org/10.3115/v1/D14-1179
Collins, J., Sohl-Dickstein, J., Sussillo, D.: Capacity and trainability in recurrent neural networks (2016). https://doi.org/10.48550/ARXIV.1611.09913
Elman, J.L.: Finding structure in time. Cogn. Sci. 14, 179–211 (1990)
Bianchini, M., Scarselli, F.: On the complexity of neural network classifiers: a comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst. 25, 1553–1565 (2014)
Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12, 2451–2471 (2000)
Graves, A., Wayne, G., Danihelka, I.: Neural turing machines (2014). https://doi.org/10.48550/ARXIV.1410.5401
Heck, J., Salem, F.M.: Simplified minimal gated unit variations for recurrent neural networks (2017). https://doi.org/10.48550/ARXIV.1701.03452
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Organization, W.H.: Covid-19 Global Death Toll. WHO Coronavirus (COVID-19) Dashboard (2019). https://covid19.who.int/data
Nwankpa, C., Ijomah, W., Gachagan, A., Marshall, S.: Activation functions: comparison of trends in practice and research for deep learning (2018). https://doi.org/10.48550/arXiv.1811.03378
Population growth (annual %) | World Bank Data. https://data.worldbank.org/indicator/SP.POP.GROW
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, A., Nasrallah, G. (2023). Gated Memory Unit: A Novel Recurrent Neural Network Architecture for Sequential Analysis. In: Wah, Y.B., Berry, M.W., Mohamed, A., Al-Jumeily, D. (eds) Data Science and Emerging Technologies. DaSET 2022. Lecture Notes on Data Engineering and Communications Technologies, vol 165. Springer, Singapore. https://doi.org/10.1007/978-981-99-0741-0_23
Download citation
DOI: https://doi.org/10.1007/978-981-99-0741-0_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0740-3
Online ISBN: 978-981-99-0741-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)