-
-
Aside from being reusable and useful on its own, it is specifically going to be useful for some upcoming algorithms, such as count-min sketch-based sparse approx nearest neighbors and for the approxim…
-
I think this project does not update anymore.
I tried to find some other similar library and found one benchmark that can compare all ANN libraries.
Well, flann performs not so good.
https://eri…
-
**Is your feature request related to a problem? Please describe.**
Google recently released a new algorithm to find Approximate Nearest Neighbors called ScaNN (https://github.com/google-research/goog…
-
A general question rather than an issue, really ---
I've been experimenting with the use of HNSW for a (very slightly) different problem than k-nearest neighbors, and wanted to ask whether it's rea…
-
Is it possible to use HDBSCAN with the Levenshtein distance? My dataset is too large to make a full distance matrix to feed into it.
The Levenshtein distance satisfies the triangle inequality whic…
-
Hi!
Great job on HDBScan, I love the library. I'm trying to cluster nearly a 100k points in a 50k dimensional space, and while i can do things like SVD to lower the dimensionality, it is still quit…
-
spacy
- A tour of awesome features of spaCy (part 1/2) - https://medium.com/eliiza-ai/a-tour-of-awesome-features-of-spacy-part-1-2-58b32425954f
- A tour of awesome features of spaCy (part 2/…
-
#### Describe the workflow you want to enable
Currently, DBSCAN is very slow for large datasets and can use a lot of memory, especially in higher dimensions.
For example, running sklearn.cluste…
-
I'm trying to replace my regular grid search with HNSW, but HNSW seems to fail rather spectacularly in finding the nearest neighbor in some cases. I understand that it's an approximate method, but it'…