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（DNN）在众多应用中展现出卓越的性能，充分体现了其处理大规模数据集的能力。然而，其静态结构限制了在动态变化环境中的适应性。本研究提出一种新型算法，使卷积神经网络（CNN）的卷积层能够根据数据输入动态演化，同时无缝集成至现有DNN中。与刚性架构不同，我们的方法通过迭代向卷积层引入核，实时评估其对变化数据的响应。该过程通过评估卷积层辨识图像特征的能力进行优化，从而引导其增长。值得注意的是，在MNIST、Fashion-MNIST、CIFAR-10和CIFAR-100等多样化数据集上，我们的无监督方法已超越有监督方法。此外，在迁移学习场景中，该方法展现出更强的适应性。通过引入数据驱动的模型可扩展性策略，我们填补了深度学习领域的空白，从而构建出更适合动态环境的更灵活高效的DNN。代码地址：(https://github.com/YunjieZhu/Extensible-Convolutional-Layer-git-version)。