Thread:Talk:DrussGT/Understanding DrussGT/Reason behind using Manhattan distance/reply (4)
(Difference between revisions)
m (Reply to Reason behind using Manhattan distance)
Latest revision as of 00:28, 28 August 2018
I have 2 hypotheses:
- Manhattan distance is more tolerant to noise than Euclidean distance. Squaring a dimension amplifies noise.
- Curse of dimensionality. Euclidean distance behaves oddly at high dimensions.