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.

本文提出了一种依赖于多输出高斯过程的人驾驶员交互的方法。该提出的方法是作为一种改进的游戏理论分层推理方法，称为“ked-k推理”，其通常将离散的行为水平分配给代理。虽然它被证明是一种有效的建模工具，但是电平推理方法可能会对由于其提取的有限数量（通常是2或3）的有限数量（通常是2或3）而言，对人类决策构成不希望的限制。提出了拟议的方法，通过引入一个连续的域框架来填补文献中的这种差距，这使得无限的政策空间能够实现。通过使用本文中呈现的方法，可以获得更精确的驱动器模型，然后可以采用该驾驶员模型，用于为自主车辆控制算法验证创建高保真仿真平台。该方法在真实的交通数据集上验证，并与传统的水平-K方法进行比较，以展示其贡献和含义。