Nish：一个新的负刺激混合激活函数
Nish: A Novel Negative Stimulated Hybrid Activation Function
摘要：
激活函数对神经网络的效率和鲁棒性具有显著影响。作为替代方案，我们发展了一种尖端的非单调激活函数，负刺激混合激活函数（Nish）。它充当正区域的整流线性单元（ReLU）函数和负区域的正弦S形函数。换句话说，它包含了一个sigmoid和一个sine函数，并在经典的ReLU上获得了新的动力学。我们分析了Nish在几个最流行的基准测试中对基本网络和最常见的激活函数的不同组合的一致性。从实验结果中，我们报告说，Nish实现的准确率略好于Mish分类。
英文摘要：
An activation function has a significant impact on the efficiency and robustness of the neural networks. As an alternative, we evolved a cutting-edge non-monotonic activation function, Negative Stimulated Hybrid Activation Function (Nish). It acts as a Rectified Linear Unit (ReLU) function for the positive region and a sinus-sigmoidal function for the negative region. In other words, it incorporates a sigmoid and a sine function and gaining new dynamics over classical ReLU. We analyzed the consistency of the Nish for different combinations of essential networks and most common activation functions using on several most popular benchmarks. From the experimental results, we reported that the accuracy rates achieved by the Nish is slightly better than compared to the Mish in classification.
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。
