arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03599cs.LGcs.AIcs.NAcs.NEmath.NA
收藏

通过扩展实现激活:一种提升神经网络性能的框架

Activations Through Extensions: A Framework To Boost Performance Of Neural Networks

IBM Research(IBM研究院);IBM T.J. Watson Research Center(IBM T.J.沃森研究中心)

Chandramouli Kamanchi, Sumanta Mukherjee, Kameshwaran Sampath, Pankaj Dayama, Arindam Jati, Vijay Ekambaram, Dzung Phan

AI总结:

本研究提出一个统一激活函数相关研究的框架,可通过激活函数操作生成神经网络的特殊泛化扩展,理论和实验均证明该扩展能以可忽略的复杂度成本提升标准测试函数及真实时间序列任务上的神经网络性能。

摘要:

激活函数是神经网络中的非线性组件,使网络能够学习输入与输出之间的复杂映射关系。常用的激活函数包括ReLU、Tanh、Sigmoid等,其选择通常取决于应用领域。在本研究中,我们提出了一个框架/策略,它统一了多项关于激活函数的研究,并从理论上解释了这些研究的性能增益来源。我们还提出了源自该框架的新技术,可通过对激活函数进行操作来获得神经网络的“扩展”(即给定神经网络的特殊泛化形式)。我们从理论和实证两方面证明,在标准测试函数上,神经网络的“扩展”相比普通神经网络具有性能优势,且空间和时间复杂度成本可忽略不计。我们还在时间序列领域的真实数据集上验证了神经网络“扩展”的增益效果。

英文摘要:

Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the application domain. In this work, we propose a framework/strategy that unifies several works on activation functions and theoretically explains the performance benefits of these works. We also propose novel techniques that originate from the framework and allow us to obtain ``extensions'' (i.e. special generalizations of a given neural network) of neural networks through operations on activation functions. We theoretically and empirically show that ``extensions'' of neural networks have performance benefits compared to vanilla neural networks with insignificant space and time complexity costs on standard test functions. We also show the benefits of neural network ``extensions'' in the time-series domain on real-world datasets.

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。

↑