标题： 深度学习完全交卡拉比-丘流形 显示英文标题

标题： Deep learning complete intersection Calabi-Yau manifolds

摘要： 我们回顾了深度学习技术在完整交点卡比拉-丘（CICY）3-和4-流形方面的进展，旨在更好地理解如何用机器学习处理代数拓扑数据。 我们首先讨论方法论方面和数据分析，然后描述神经网络架构。 接着，我们描述了预测Hodge数的最新准确度。 我们包含了关于从低Hodge数外推到高Hodge数以及相反方向的新结果。 显示英文摘要

摘要： We review advancements in deep learning techniques for complete intersection Calabi-Yau (CICY) 3- and 4-folds, with the aim of understanding better how to handle algebraic topological data with machine learning. We first discuss methodological aspects and data analysis, before describing neural networks architectures. Then, we describe the state-of-the art accuracy in predicting Hodge numbers. We include new results on extrapolating predictions from low to high Hodge numbers, and conversely.