| Issue |
ITM Web Conf.
Volume 47, 2022
2022 2nd International Conference on Computer, Communication, Control, Automation and Robotics (CCCAR2022)
|
|
|---|---|---|
| Article Number | 02046 | |
| Number of page(s) | 6 | |
| Section | Algorithm Optimization and Application | |
| DOI | https://doi.org/10.1051/itmconf/20224702046 | |
| Published online | 23 June 2022 | |
Research on recurrent neural network model based on weight activity evaluation
1 School of Information Engineering, Wuhan Institute of Design and Sciences, Wuhan, Hubei, China
2 School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan, Hubei, China
* Corresponding author: kristoffzc@163.com
Given the complex structure and parameter redundancy of recurrent neural networks such as LSTM, related research and analysis on the structure of recurrent neural networks have been done. To improve the structural rationality of the recurrent neural network and reduce the amount of calculation of network parameters, a weight activity evaluation algorithm is proposed that evaluates the activity of the basic unit of the network. Through experiments and tests on arrhythmia data, the differences in the weight activity of the LSTM network and the change characteristics of weights and gradients are analyzed. The experimental results show that this algorithm can better optimize the recurrent neural network structure and reduce the redundancy of network parameters.
Key words: Weight activity evaluation / Parameter redundancy / Recurrent neural network
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.