arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.14545cs.LGcs.NE
收藏

深度学习中的激活函数:全面调查和基准测试

Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark

Indian Institute of Information Technology, Allahabad(印度理工学院信息技术学院(阿拉哈巴德));Techno India University(泰克诺印度大学);Indian Statistical Institute(印度统计研究所)

Shiv Ram Dubey, Satish Kumar Singh, Bidyut Baran Chaudhuri

摘要:

近年来,神经网络在解决众多问题方面取得了巨大的发展。已经引入了各种类型的神经网络来处理不同类型的问题。然而,任何神经网络的主要目标都是使用分层结构将非线性可分离的输入数据转换为更线性可分离的抽象特征。这些层是线性和非线性函数的组合。最流行和最常见的非线性层是激活函数(AF),例如Logistic Sigmoid、Tanh、ReLU、ELU、Swish和Mish。本文对用于深度学习的神经网络中的AF进行了全面的概述和调查。涵盖了不同类别的AF,如基于Logistic Sigmoid和Tanh,基于ReLU,基于ELU和基于学习。指出了自适应滤波器的输出范围、单调性和平滑性等特性。还进行了性能比较之间的18个国家的最先进的AF与不同的网络对不同类型的数据。提出了AF的见解,以利于研究人员做进一步的研究和从业人员在不同的选择中进行选择。用于实验比较的代码发布于:\url{https://github.com/shivram1987/ActivationFunctions}。

英文摘要:

Neural networks have shown tremendous growth in recent years to solve numerous problems. Various types of neural networks have been introduced to deal with different types of problems. However, the main goal of any neural network is to transform the non-linearly separable input data into more linearly separable abstract features using a hierarchy of layers. These layers are combinations of linear and nonlinear functions. The most popular and common non-linearity layers are activation functions (AFs), such as Logistic Sigmoid, Tanh, ReLU, ELU, Swish and Mish. In this paper, a comprehensive overview and survey is presented for AFs in neural networks for deep learning. Different classes of AFs such as Logistic Sigmoid and Tanh based, ReLU based, ELU based, and Learning based are covered. Several characteristics of AFs such as output range, monotonicity, and smoothness are also pointed out. A performance comparison is also performed among 18 state-of-the-art AFs with different networks on different types of data. The insights of AFs are presented to benefit the researchers for doing further research and practitioners to select among different choices. The code used for experimental comparison is released at: \url{https://github.com/shivram1987/ActivationFunctions}.

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。

↑