Abstract: Reliable fault diagnosis in power transformers is paramount for ensuring grid stability and safeguarding critical assets. This paper proposes a novel deep learning-based diagnostic framework ...

Abstract: The integration of Deep Semi-Supervised Learning (DSSL) with Continual Learning (CL) holds significant promise for advancing artificial intelligence systems capable of learning from limited ...

This package is currently in active development and may not work as expected. Use at your own risk. Breaking changes may occur in future versions. The goal of this project is to provide a lightweight, ...

The efficacy of deep residual networks is fundamentally predicated on the identity shortcut connection. While this mechanism effectively mitigates the vanishing gradient problem, it imposes a strictly ...