Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This research presents a new algorithm that allows the convolutional layer of a Convolutional Neural Network (CNN) to dynamically evolve based on data input, while still being seamlessly integrated into existing DNNs. Instead of a rigid architecture, our approach iteratively introduces kernels to the convolutional layer, gauging its real-time response to varying data. This process is refined by evaluating the layer's capacity to discern image features, guiding its growth. Remarkably, our unsupervised method has outstripped its supervised counterparts across diverse datasets like MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. It also showcases enhanced adaptability in transfer learning scenarios. By introducing a data-driven model scalability strategy, we are filling a void in deep learning, leading to more flexible and efficient DNNs suited for dynamic settings. Code:(https://github.com/YunjieZhu/Extensible-Convolutional-Layer-git-version).

翻译：深度神经网络（DNNs）已在众多应用中展现出卓越的成就，体现了其处理海量数据集的能力。然而，其静态结构限制了其在动态变化环境中的适应性。本研究提出一种新算法，允许卷积神经网络（CNN）中的卷积层根据数据输入动态演化，同时仍能无缝集成到现有DNNs中。不同于僵化的架构，我们的方法通过迭代向卷积层引入卷积核，实时评估其对不同数据的响应。该过程通过分析层对图像特征的辨识能力进行优化，从而指导其增长。值得注意的是，我们的无监督方法在MNIST、Fashion-MNIST、CIFAR-10和CIFAR-100等多个数据集上均超越了有监督方法。在迁移学习场景中，该方法还展现出更强的适应性。通过引入数据驱动的模型可扩展策略，我们填补了深度学习领域的空白，从而构建出更灵活高效的DNNs，以适应动态环境。代码地址：(https://github.com/YunjieZhu/Extensible-Convolutional-Layer-git-version)。