LiteLSTM Architecture Based on Weights Sharing for Recurrent Neural Networks
Not on the map. Why?
Abstract (arXiv)
Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This paper proposed a novel LiteLSTM architecture based on reducing the LSTM computation components via the weights sharing concept to reduce the overall architecture computation cost and maintain the architecture performance. The proposed LiteLSTM can be significant for processing large data where time-consuming is crucial while hardware resources are limited, such as the security of IoT devices and medical data processing. The proposed model was evaluated and tested empirically on three different datasets from the computer vision, cybersecurity, speech emotion recognition domains. The proposed LiteLSTM has comparable accuracy to the other state-of-the-art recurrent architecture while using a smaller computation budget.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 70 references that are in the map. First posted on arXiv 12 Jan 2023.
Builds on
29 of 70 references.
References · 29
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
- 2015LSTM: A Search Space Odysseycited by 315
- 2017Regularizing and Optimizing LSTM Language Modelscited by 205
- 2017LSTM Fully Convolutional Networks for Time Series Classificationcited by 135
- 2018Multivariate LSTM-FCNs for Time Series Classificationcited by 120
- 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
- 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
17 more
- 2017Tensor-Train Recurrent Neural Networks for Video Classificationcited by 59
- 2016Noisy Activation Functionscited by 53
- 2014Addressing the Rare Word Problem in Neural Machine Translationcited by 50
- 2016Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognitioncited by 33
- 2019Fast Multi-language LSTM-based Online Handwriting Recognitioncited by 22
- 2020Global Feature Aggregation for Accident Anticipationcited by 17
- 2015Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentationcited by 16
- 2022Speech Emotion Recognition using Supervised Deep Recurrent System for Mental Health Monitoringcited by 15
- 2016A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognitioncited by 10
- 2022Review on Action Recognition for Accident Detection in Smart City Transportation Systemscited by 8
- 2016Gated Word-Character Recurrent Language Modelcited by 5
- 2018Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Predictioncited by 5
- 2022LiteLSTM Architecture for Deep Recurrent Neural Networkscited by 5
- 2022Baby Physical Safety Monitoring in Smart Home Using Action Recognition Systemcited by 4
- 2021Intrusion Detection System in Smart Home Network Using Bidirectional LSTM and Convolutional Neural Networks Hybrid Modelcited by 3
- 2016Handwriting recognition using Cohort of LSTM and lexicon verification with extremely large lexiconcited by 2
- 2021Autonomous Low Power IoT System Architecture for Cybersecurity Monitoringcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.