Score: 1

VeLU: Variance-enhanced Learning Unit for Deep Neural Networks

Published: April 21, 2025 | arXiv ID: 2504.15051v1

By: Ashkan Shakarami , Yousef Yeganeh , Azade Farshad and more

Potential Business Impact:

Makes computer brains learn faster and better.

Business Areas:
A/B Testing Data and Analytics

Activation functions are fundamental in deep neural networks and directly impact gradient flow, optimization stability, and generalization. Although ReLU remains standard because of its simplicity, it suffers from vanishing gradients and lacks adaptability. Alternatives like Swish and GELU introduce smooth transitions, but fail to dynamically adjust to input statistics. We propose VeLU, a Variance-enhanced Learning Unit as an activation function that dynamically scales based on input variance by integrating ArcTan-Sin transformations and Wasserstein-2 regularization, effectively mitigating covariate shifts and stabilizing optimization. Extensive experiments on ViT_B16, VGG19, ResNet50, DenseNet121, MobileNetV2, and EfficientNetB3 confirm VeLU's superiority over ReLU, ReLU6, Swish, and GELU on six vision benchmarks. The codes of VeLU are publicly available on GitHub.

Country of Origin
🇩🇪 🇮🇹 Germany, Italy

Page Count
20 pages

Category
Computer Science:
Machine Learning (CS)