Design and Implementation of LSTM Accelerator Based on FPGA

Zhang, Weifeng; Feng, Guorui; Cui, Chenchen; Yang, Ying; Fang, Zhou; Wu, Ning

doi:10.1109/icct50939.2020.9295665

Cited by 12 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While traditional LSTM models only consider time-series dependencies, ConvLSTM combines the strengths of LSTM and convolutional neural networks (CNN), allowing it to effectively capture spatiotemporal dependencies and model both temporal and spatial dimensions [27]. Additionally, traditional LSTM primarily relies on matrix multiplication and element-wise operations [28], which limits its capacity to model data nonlinearly. In contrast, by utilizing multiple filters and the local connectivity of the convolution kernel, ConvLSTM can learn richer feature representations and extract more complex spatiotemporal patterns in the data.…”

Section: Discussionmentioning

confidence: 99%

An Integrated Framework for Spatiotemporally Merging Multi-Sources Precipitation Based on F-SVD and ConvLSTM

et al. 2023

View full text Add to dashboard Cite

To improve the accuracy and reliability of precipitation estimation, numerous models based on machine learning technology have been developed for integrating data from multiple sources. However, little attention has been paid to extracting the spatiotemporal correlation patterns between satellite products and rain gauge observations during the merging process. This paper focuses on this issue by proposing an integrated framework to generate an accurate and reliable spatiotemporal estimation of precipitation. The proposed framework integrates Funk-Singular Value Decomposition (F-SVD) in the recommender system to achieve the accurate spatial distribution of precipitation based on the spatiotemporal interpolation of rain gauge observations and Convolutional Long Short-Term Memory (ConvLSTM) to merge precipitation data from interpolation results and satellite observation through exploiting the spatiotemporal correlation pattern between them. The framework (FS-ConvLSTM) is utilized to obtain hourly precipitation merging data with a resolution of 0.1° in Jianxi Basin, southeast of China, from both rain gauge data and Global Precipitation Measurement (GPM) from 2006 to 2018. The LSTM and Inverse Distance Weighting (IDW) are constructed for comparison purposes. The results demonstrate that the framework could not only provide more accurate precipitation distribution but also achieve better stability and reliability. Compared with other models, it performs better in variation process description and rainfall capture capability, and the root mean square error (RSME) and probability of detection (POD) are improved by 63.6% and 22.9% from the original GPM, respectively. In addition, the merged precipitation combines the strength of different data while mitigating their weaknesses and has good agreement with observed precipitation in terms of magnitude and spatial distribution. Consequently, the proposed framework provides a valuable tool to improve the accuracy of precipitation estimation, which can have important implications for water resource management and natural disaster preparedness.

show abstract

Section: Discussionmentioning

confidence: 99%

An Integrated Framework for Spatiotemporally Merging Multi-Sources Precipitation Based on F-SVD and ConvLSTM

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The control unit structure of LSTM is shown in Figure 1 below. 5 In order to avoid the problem of long-term dependence of time series in the LSTM network structure, a special design was made for RNN neurons. This design simulates human memory patterns and controls memory units through three gates: "forgetting gate", "input gate", and "output gate", as well as a "cell state" to record historical information.…”

Section: Principles Of Lstm Algorithmmentioning

confidence: 99%

Human resource attendance mechanism based on the internet of things: A method based on data fusion

Shen

2023

Internet Technology Letters

View full text Add to dashboard Cite

The development of Internet of Things technology makes people need to deal with an increasing amount of data, which brings the poor data quality, fast data generation speed and other problems. These problems have become one of the main obstacles restricting the development of human resource attendance. At present, data fusion methods as important methods in data fusion technology. This article fully utilizes human resource attendance data and proposes the LSTM‐Attention data fusion method. This method uses LSTM to model the data, extract potential features of the data, and filter out meaningful data in the human resource attendance mechanism through the Attention mechanism to achieve data fusion. Finally, experimental results in this article showed that the LSTM‐Attention data fusion method designed in this article has higher prediction accuracy. It fully mines the correlation between data, and further improves the accuracy of analysis and prediction in the human resource attendance mechanism based on the Internet of Things.

show abstract

A Reconfigurable Inference Processor for Recurrent Neural Networks Based on Programmable Data Format in a Resource-Limited FPGA

Kim

Park

Kim

2022

2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC)

View full text Add to dashboard Cite

Design and Implementation of LSTM Accelerator Based on FPGA

Cited by 12 publications

References 10 publications

An Integrated Framework for Spatiotemporally Merging Multi-Sources Precipitation Based on F-SVD and ConvLSTM

An Integrated Framework for Spatiotemporally Merging Multi-Sources Precipitation Based on F-SVD and ConvLSTM

Human resource attendance mechanism based on the internet of things: A method based on data fusion

A Reconfigurable Inference Processor for Recurrent Neural Networks Based on Programmable Data Format in a Resource-Limited FPGA

Contact Info

Product

Resources

About