Adaptive Activation Function Generation for Artificial Neural Networks through Fuzzy Inference with Application in Grooming Text Categorisation

Zuo, Zheming, Li, Jie, Wei, Bo, Yang, Longzhi, Chao, Fei and Naik, Nitin (2019) Adaptive Activation Function Generation for Artificial Neural Networks through Fuzzy Inference with Application in Grooming Text Categorisation. In: 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2019): New Orleans, Louisiana, USA 23 – 26 June 2019. IEEE, Piscataway, NJ, pp. 1180-1186. ISBN 9781538617298, 9781538617281

Preview

Text Zuo et al - Adaptive Activation Function Generation for Artificial Neural Networks AAM.pdf - Accepted Version Download (14MB) | Preview

Abstract

The activation function is introduced to determine the output of neural networks by mapping the resulting values of neurons into a specific range. The activation functions often suffer from `gradient vanishing', `non zero-centred function outputs', `exploding gradients', and `dead neurons', which may lead to deterioration in the classification performance. This paper proposes an activation function generation approach using the Takagi-Sugeno-Kang inference in an effort to address such challenges. In addition, the proposed method further optimises the coefficients in the activation function using the genetic algorithm such that the activation function can adapt to different applications. This approach has been applied to a digital forensics application of online grooming detection. The evaluations confirm the superiority of the proposed activation function for online grooming detection using an unbalanced data set.

Actions (login required)

View Item

Downloads