arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02523cs.LG
收藏

有监督深度神经网络的最新激活函数分析

An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network

Ho Chi Minh City University of Technology, Vietnam National University - Ho Chi Minh(胡志明市理工大学,越南国立大学胡志明市分校);University of Technology and Education HCMC(胡志明市技术教育大学);Da Nang University of Science and Technology(岘港科技大学);Austrian Institute of Technology(奥地利理工学院)

Anh Nguyen, Khoa Pham, Dat Ngo, Thanh Ngo, Lam Pham

摘要:

本文提供了关于深度神经网络的监督分类的最新激活函数的分析。这些激活函数包括整流线性单元(ReLU)、指数线性单元(ELU)、缩放指数线性单元(SELU)、高斯误差线性单元(GELU)和逆平方根线性单元(ISRLU)。为了评估,在集成这些激活函数的两个深度学习网络架构上进行实验。第一个模型,基于多层感知器(MLP),评估与MNIST数据集执行这些激活函数。同时,第二个模型,可能是基于VGGish的架构,应用于DCASE 2018挑战中的声学场景分类(ASC)任务1A,从而评估这些激活函数是否在不同的数据集以及不同的网络架构中工作良好。

英文摘要:

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions. Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑