论文标题
机器学习的通用激活功能
Universal Activation Function For Machine Learning
论文作者
论文摘要
本文提出了一个通用激活函数（UAF），该功能在量化，分类和加强学习（RL）问题方面取得了几乎最佳的性能。对于任何给定的问题，优化算法能够通过调整UAF的参数来将UAF演变为合适的激活函数。对于CIFAR-10分类和VGG-8，UAF会收敛到Mish，例如激活功能，与其他激活功能相比，它几乎具有最佳性能$ f_ {1} = 0.9017 \ pm0.0040 $。为了定量30 dB信噪比（SNR）环境中的模拟9-GAS混合物，UAF收敛到身份函数，其身份函数接近最佳的根平方误差为$ 0.4888 \ pm 0.0032 $ $ $μm$。在BipedalWalker-V2 RL数据集中，UAF以$ 961 \ pm 193 $时代获得了250奖励，这证明了UAF在最低时期的时代收敛。此外，UAF收敛到BipedalWalker-V2 RL数据集中的新激活函数。
This article proposes a Universal Activation Function (UAF) that achieves near optimal performance in quantification, classification, and reinforcement learning (RL) problems. For any given problem, the optimization algorithms are able to evolve the UAF to a suitable activation function by tuning the UAF's parameters. For the CIFAR-10 classification and VGG-8, the UAF converges to the Mish like activation function, which has near optimal performance $F_{1} = 0.9017\pm0.0040$ when compared to other activation functions. For the quantification of simulated 9-gas mixtures in 30 dB signal-to-noise ratio (SNR) environments, the UAF converges to the identity function, which has near optimal root mean square error of $0.4888 \pm 0.0032$ $μM$. In the BipedalWalker-v2 RL dataset, the UAF achieves the 250 reward in $961 \pm 193$ epochs, which proves that the UAF converges in the lowest number of epochs. Furthermore, the UAF converges to a new activation function in the BipedalWalker-v2 RL dataset.
