TY - JOUR
T1 - VPNET: Variable Projection Networks
AU - Kovács, Péter
AU - Bognár, Gergo
AU - Huber, Christian
AU - Huemer, Mario
PY - 2021/10/13
Y1 - 2021/10/13
N2 - In this paper, 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.
AB - In this paper, 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.
UR - http://dx.doi.org/10.1142/s0129065721500544
U2 - 10.1142/s0129065721500544
DO - 10.1142/s0129065721500544
M3 - Article
SN - 0129-0657
JO - International Journal of Neural Systems
JF - International Journal of Neural Systems
ER -