Log in
Research report
金工深度研究：Attention is indeed all you need-20230822-华泰证券-24页
人工智能系列之69：注意力机制应用于量化选股多类场景 注意力机制是近年来人工智能领域影响深远的创新之一，但以往应用于量化投资多局限在行情时间序列编码，本研究展示多种形式的注意力机制在量化选股各类场景的运用。分别测试：(1)任务间注意力：提取多任务学习中的任务间关系信息；(2)股票间注意力：Transformer学习截面因子的股票间关系；(3)时序注意力：ALSTM和Transformer编码因子时
Read full report →Related industries
No related institutions
Similar reports
- Knowing When to Stop: The Art of Making a Loop Converge
- Work-Study Programs Improve Young Women's Long-Term Labor Market Outcomes
- Sahel and West Africa Coastal Countries (SAWAC) Umbrella Program: 2026 Communications and Visibility Plan
- Scaling What Works: Integrated Social Protection Reforms for Poverty Reduction and Upward Mobility in Ghana