.png){kind=icon}
Return
Developing Novel Activation Functions Based Deep Learning LSTM for Classification
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3205774.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study proposes novel Long Short-Term Memory (LSTM)-based classifiers through developing the internal structure of LSTM neural networks using 26 state activation functions as alternatives to the traditional hyperbolic tangent (tanh) activation function. The LSTM networks have high performance in solving the vanishing gradient problem that is observed in recurrent neural networks. Performance investigations were carried out utilizing three distinct deep learning optimization algorithms to evaluate the efficiency of the proposed state activation functions-based LSTM classifiers for two different classification tasks. The simulation results demonstrate that the proposed classifiers that use the Modified Elliott, Softsign, Sech, Gaussian, Bitanh1, Bitanh2 and Wave as state activation functions trump the tanh-based LSTM classifiers in terms of classification accuracy. The proposed classifiers are encouraged to be utilized and tested for other classification tasks.
Keywords:
Logic gates
Computer architecture
Microprocessors
Deep learning
Neural networks
Task analysis
Recurrent neural networks
Long short term memory
Classification algorithms
LSTM
deep neural network
activation function
tanh gate
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveTrajectory Planning and Resource Allocation of Multiple UAVs for Data Delivery in Vehicular Networks
PREAI
ShareSaveShareSaveShareSave
View more