Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning

Researchers have developed a new activation function called squared sigmoid-tanh (SST) designed to improve the performance of Gated Recurrent Units (GRUs) in sequence learning tasks, particularly when training data is limited. This parameter-free modification enhances the contrast between gate activations, leading to sharper information filtering and more stable learning. Evaluations across sign language recognition, human activity recognition, and time-series forecasting demonstrated that SST-GRUs consistently outperform standard GRUs, especially in data-scarce environments, with minimal added computational cost. AI

影响 Introduces a parameter-free modification to GRUs that improves performance in low-data sequence learning scenarios.

排序理由 This is a research paper introducing a novel activation function for recurrent neural networks.

在 arXiv cs.LG 阅读 →

• arXiv
• tanh
• sign language recognition
• human activity recognition
• time-series forecasting

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →