2020/12/11 by Stamatis Mastromichalakis, Mastromichalakis, Stamatis · 1 citation
Computer Science · #68T07 #68T10 #68T45 #68T50 #68U35 #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Stochastic Gradient Optimization Techniques
paper · pdf · doi:10.48550/arxiv.2012.07564
openalex publication_date 2020/12/11 · openalex created_date 2021/01/05 · openalex updated_date 2026/07/28
Despite the unresolved 'dying ReLU problem', the classical ReLU activation function (AF) has been extensively applied in Deep Neural Networks (DNN), in particular Convolutional Neural Networks (CNN), for image classification. The common gradient issues of ReLU pose challenges in applications on academy and industry sectors. Recent approaches for improvements are in a similar direction by just proposing variations of the AF, such as Leaky ReLU (LReLU), while maintaining the solution within the same unresolved gradient problems. In this paper, the Absolute Leaky ReLU (ALReLU) AF, a variation of LReLU, is proposed, as an alternative method to resolve the common 'dying ReLU problem' on NN-based algorithms for supervised learning. The experimental results demonstrate that by using the absolute values of LReLU's small negative gradient, has a significant improvement in comparison with LReLU and ReLU, on image classification of diseases such as COVID-19, text and tabular data classification tasks on five different datasets.