聚焦欧洲央行-基于深度神经网络的DSGE模型的序贯解(英)-2026。The results support a clear practical recommendation: shallow networks of two to three layers, moderate width of 32 neurons, and an intermediate steady state penalty weight of λss = 1 consistently deliver the best accuracy at the lowest computational cost.
聚焦欧洲央行-基于深度神经网络的DSGE模型的序贯解(英)-2026。The results support a clear practical recommendation: shallow networks of two to three layers, moderate width of 32 neurons, and an intermediate steady state penalty weight of λss = 1 consistently deliver the best accuracy at the lowest computational cost.
聚焦欧洲央行-基于深度神经网络的DSGE模型的序贯解(英)-2026。The results support a clear practical recommendation: shallow networks of two to three layers, moderate width of 32 neurons, and an intermediate steady state penalty weight of λss = 1 consistently deliver the best accuracy at the lowest computational cost.
覆盖 2026 年,全文共 66 页。
本报告为付费报告,可在资料宝站内下单后获取完整内容。
重点分析了欧洲央行等议题。