mlsanityData to 14 Oct 2026

LiteLSTM Architecture for Deep Recurrent Neural Networks

arXiv 2201.11624 ↗First posted 27 Jan 2022cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware aspects. This paper proposes a novel LiteLSTM architecture based on reducing the computation components of the LSTM using the weights sharing concept to reduce the overall architecture cost and maintain the architecture performance. The proposed LiteLSTM can be significant for learning big data where time-consumption is crucial such as the security of IoT devices and medical data. Moreover, it helps to reduce the CO2 footprint. The proposed model was evaluated and tested empirically on two different datasets from computer vision and cybersecurity domains.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 19 of its 38 references that are in the map. First posted on arXiv 27 Jan 2022.

Builds on

19 of 38 references.

References · 19

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  2. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  6. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
  7. 2015LSTM: A Search Space Odysseycited by 316
  8. 2017Regularizing and Optimizing LSTM Language Modelscited by 205
  9. 2017LSTM Fully Convolutional Networks for Time Series Classificationcited by 136
  10. 2018Multivariate LSTM-FCNs for Time Series Classificationcited by 120
  11. 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
  12. 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
7 more
  1. 2017Tensor-Train Recurrent Neural Networks for Video Classificationcited by 59
  2. 2016Noisy Activation Functionscited by 53
  3. 2014Addressing the Rare Word Problem in Neural Machine Translationcited by 50
  4. 2016Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognitioncited by 33
  5. 2015Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentationcited by 16
  6. 2016Gated Word-Character Recurrent Language Modelcited by 5
  7. 2018Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Predictioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 0; 2026: 1.

5 papers.

  1. 2024Millimeter Wave Radar-based Human Activity Recognition for Healthcare Monitoring Robotcited by 5
  2. 2024Asynchronous and Segmented Bidirectional Encoding for NMTcited by 2
  3. 2024Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networkscited by 2
  4. 2023LiteLSTM Architecture Based on Weights Sharing for Recurrent Neural Networkscited by 1
  5. 2026Targeted Adversarial Traffic Generation : Black-box Approach to Evade Intrusion Detection Systems in IoT Networkscited by 0