Developing Novel Activation Functions Based Deep Learning LSTM for Classification

Abstract

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.