Artificial neural networks (ANNs) have permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors. However, the inherent limitations of traditional neural networks arise due to their relatively fixed network structures and activation functions. 1, The type of activation function is single and relatively fixed, which leads to poor "unit representation ability" of the network, and it is often used to solve simple problems with very complex networks; 2, the network structure is not adaptive, it is easy to cause network structure redundant or insufficient. To address the aforementioned issues, this study proposes a novel neural network called X-Net. By utilizing our designed Alternating Backpropagation mechanism, X-Net dynamically selects appropriate activation functions based on derivative information during training to enhance the network's representation capability for specific tasks. Simultaneously, it accurately adjusts the network structure at the neuron level to accommodate tasks of varying complexities and reduce computational costs. Through a series of experiments, we demonstrate the dual advantages of X-Net in terms of reducing model size and improving representation power. Specifically, in terms of the number of parameters, X-Net is only 3$\%$ of baselines on average, and only 1.4$\%$ under some tasks. In terms of representation ability, X-Net can achieve an average $R^2$=0.985 on the fitting task by only optimizing the activation function without introducing any parameters. Finally, we also tested the ability of X-Net to help scientific discovery on data from multiple disciplines such as society, energy, environment, and aerospace, and achieved concise and good results.

翻译：人工神经网络已渗透至生物信息学到金融分析等多个学科领域，成为当代科研工作中不可或缺的组成部分。然而，传统神经网络因网络结构及激活函数相对固定而存在固有局限性：1)激活函数类型单一且相对固定，导致网络"单元表征能力"较弱，常需以极复杂网络解决简单问题；2)网络结构缺乏自适应性，易引发网络结构冗余或容量不足。针对上述问题，本研究提出一种名为X-Net的新型神经网络。通过利用我们设计的交替反向传播机制，X-Net可在训练过程中依据导数信息动态选取合适的激活函数，从而增强网络对特定任务的表征能力；同时，它能在神经元层级精确调整网络结构，以适应不同复杂程度的任务并降低计算开销。通过系列实验，我们证明了X-Net在缩减模型规模与提升表征能力方面的双重优势。具体而言：在参数量方面，X-Net平均仅为基线模型的3%，部分任务下仅占1.4%；在表征能力方面，X-Net可在不引入任何参数的情况下仅通过优化激活函数实现拟合任务平均$R^2$=0.985。最后，我们还在社会、能源、环境及航空航天等多学科数据的科学发现任务中测试了X-Net的辅助能力，均取得了简洁且优异的效果。