Simplified gating in long short-term memory (LSTM) recurrent neural networks

Lu, Yutong; Salem, Fathi M.

doi:10.1109/mwscas.2017.8053244

Cited by 38 publications

(18 citation statements)

References 17 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is the activity tag value corresponding to the sequential infrared signal of the L frame. By comparing the output value with the label value, the gradient descent [35] method is used to iteratively update the parameters in the network through the backpropagation [36] process of the network. The collected sequential infrared signals will be trained through the above method.…”

Section: Model Trainingmentioning

confidence: 99%

Device-Free Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Long Short-Term Memory Neural Network

Yin

Chen

Miao

et al. 2021

Sensors

View full text Add to dashboard Cite

Sensor-based human activity recognition (HAR) has attracted enormous interests due to its wide applications in the Internet of Things (IoT), smart homes and healthcare. In this paper, a low-resolution infrared array sensor-based HAR approach is proposed using the deep learning framework. The device-free sensing system leverages the infrared array sensor of 8×8 pixels to collect the infrared signals, which can ensure users’ privacy and effectively reduce the deployment cost of the network. To reduce the influence of temperature variations, a combination of the J-filter noise reduction method and the Butterworth filter is performed to preprocess the infrared signals. Long short-term memory (LSTM), a representative recurrent neural network, is utilized to automatically extract characteristics from the infrared signal and build the recognition model. In addition, the real-time HAR interface is designed by embedding the LSTM model. Experimental results show that the typical daily activities can be classified with the recognition accuracy of 98.287%. The proposed approach yields a better result compared to the existing machine learning methods, and it provides a low-cost yet promising solution for privacy-preserving scenarios.

show abstract

Section: Model Trainingmentioning

confidence: 99%

Device-Free Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Long Short-Term Memory Neural Network

Yin

Chen

Miao

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Here, we explore further the first three SLIM LSTM variants, denoted as LSTM1, LSTM2, and LSTM3 as termed in [6], [7], [10], [11].…”

Section: B Slim Lstm Variants Overviewmentioning

confidence: 99%

Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer

Kent

Salem

2019

2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)

View full text Add to dashboard Cite

The Long Short-Term Memory (LSTM) layer is an important advancement in the field of neural networks and machine learning, allowing for effective training and impressive inference performance. LSTM-based neural networks have been successfully employed in various applications such as speech processing and language translation. The LSTM layer can be simplified by removing certain components, potentially speeding up training and runtime with limited change in performance. In particular, the recently introduced variants, called SLIM LSTMs, have shown success in initial experiments to support this view. Here, we perform computational analysis of the validation accuracy of a convolutional plus recurrent neural network architecture using comparatively the standard LSTM and three SLIM LSTM layers. We have found that some realizations of the SLIM LSTM layers can potentially perform as well as the standard LSTM layer for our considered architecture.

show abstract

“…This second approach tackle hate speech detection trough neural networks (Schmidt and Wiegand, 2017). In this stage, we used several neural networks architectures which works enough well with text, some of them are: Convolutional Neural Networks (CNN) (Jacovi et al, 2018), Long short term memory (LSTM) and its variations: Peephole, Bidirectional (BILSTM) and Gated Recurrent Unit (GRU) (Lu and Salem, 2017). We tested these architectures with different corpora which were slightly modified, in some cases we used a corpus with stop words, or simply a stemming or a lemmatized version of words.…”

Section: Based On Nnmentioning

confidence: 99%

HATERecognizer at SemEval-2019 Task 5: Using Features and Neural Networks to Face Hate Recognition

Nina-Alcocer¹

2019

Proceedings of the 13th International Workshop on Semantic Evaluation

View full text Add to dashboard Cite

This paper presents a detailed description of our participation in task 5 on SemEval-2019 1. This task consists of classifying English and Spanish tweets that contain hate towards women or immigrants. We carried out several experiments; for a finer-grained study of the task, we analyzed different features and designing architectures of neural networks. Additionally, to face the lack of hate content in tweets, we include data augmentation as a technique to increase hate content in our datasets.

show abstract

Simplified gating in long short-term memory (LSTM) recurrent neural networks

Cited by 38 publications

References 17 publications

Device-Free Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Long Short-Term Memory Neural Network

Device-Free Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Long Short-Term Memory Neural Network

Performance of Three Slim Variants of The Long Short-Term Memory (LSTM) Layer

HATERecognizer at SemEval-2019 Task 5: Using Features and Neural Networks to Face Hate Recognition

Contact Info

Product

Resources

About