We give explicit theoretical and heuristical bounds for how big does a data set sampled from a reach-1 submanifold M of euclidian space need to be, to be able to estimate the dimension of M with 90% confidence.
翻译:我们给出明确的理论和逻辑界限, 说明从优利安空间的 达到-1 亚磁M 样本中提取的数据集有多大, 才能以 90% 的置信度来估计M 的尺寸。