deep neural networks have been shown to be beneficial for a variety of tasks,
in particular allowing for end-to-end learning and reducing the requirement for
manual design decisions. However, still many parameters have to be chosen in
advance, also raising the need to optimize them. On
本研究旨在通过研究两种类型的自适应激活函数来填补理解有限数据情景下可变激活函数对分类准确性和预测不确定性的影响的重要空白。研究结果表明，具有个体训练参数的自适应激活函数（如 ELU 和 Softplus）能够产生准确且自信的预测模型，优于固定形状激活函数和在隐藏层中使用相同可训练激活函数的不太灵活的方法。因此，该研究提供了在科学和工程问题中设计自适应神经网络的简洁方法。