论文标题
VPNET：可变投影网络
VPNet: Variable Projection Networks
论文作者
论文摘要
我们介绍了基于变量投影（VP）的新型模型驱动的神经网络体系结构VPNET。将VP操作员应用于神经网络会导致可学习的功能，可解释的参数和紧凑的网络结构。本文讨论了VPNET的动机和数学背景，并进行了展示实验。在信号处理的背景下评估了VPNET方法，我们将合成数据集和真实心电图（ECG）信号分类。与完全连接和一维卷积网络相比，VPNET在培训和推理的低计算成本下具有快速学习能力和良好的准确性。基于这些优势和获得的有希望的结果，我们预计对更广泛的信号处理领域产生深远影响，尤其是对分类，回归和聚类问题。
We introduce VPNet, a novel model-driven neural network architecture based on variable projection (VP). Applying VP operators to neural networks results in learnable features, interpretable parameters, and compact network structures. This paper discusses the motivation and mathematical background of VPNet and presents experiments. The VPNet approach was evaluated in the context of signal processing, where we classified a synthetic dataset and real electrocardiogram (ECG) signals. Compared to fully connected and one-dimensional convolutional networks, VPNet offers fast learning ability and good accuracy at a low computational cost of both training and inference. Based on these advantages and the promising results obtained, we anticipate a profound impact on the broader field of signal processing, in particular on classification, regression and clustering problems.
