FE-RNN: a fuzzy embedded recurrent neural network for improving interpretability of underlying neural network
Deep learning enables effective predictions. But deep structures face some challenges on human interpretability compared to conventional techniques, e.g., fuzzy inference systems. It motivates more research works to alleviate the black box nature of deep structures with performance maintained. This...
Saved in:
Main Authors: | Tan, James Chee Min, Cao, Qi, Quek, Chai |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Article |
語言: | English |
出版: |
2024
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/178712 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Increasing interpretability using a fuzzy-embedded recurrent neural network (FE-RNN) with its application in stock ETF trading
由: Tan, James Chee Min
出版: (2021) -
An interpretable Neural Fuzzy Hammerstein-Wiener network for stock price prediction
由: Xie, Chen, et al.
出版: (2022) -
Artificial neural network for tsunami forecasting
由: Romano, M., et al.
出版: (2014) -
Towards interpreting recurrent neural networks through probabilistic abstraction
由: DONG, Guoliang, et al.
出版: (2020) -
Building energy consumption raw data forecasting using data cleaning and deep recurrent neural networks
由: Yang, J., et al.
出版: (2022)