-
Suggest a paper you would like us to discuss in our next meeting. You can upvote a paper using the :thumbsup: emoji.
The paper with the most upvotes by the end of the week (Friday) will be chosen.
-
We have two desiderata:
1. We want to be able to learn a network which regresses to measurements given a structure as input.
2. We may want to pretrain parts of that network (i.e. the molecular re…
-
**Describe the bug**
I have a problem using the UnsupervisedDetector models in a pipeline. I have tried a two different simple linear pipelines, one with a standardizer and LOFDetector and one with…
-
## Traceback:
```py
RuntimeError Traceback (most recent call last)
in ()
19
20 # Run inference using the instantiated models
---> 21 answers = model.get_…
-
Clustering models in MLJ are implemented as `Unsupervised`
models. While they share common functionality, this has not been
properly documented, and there is no model subtype or trait that tags
a m…
-
Can VAR do super resolution like GigaGan super resolution for example. Gigagan is the most impressive super resolution algorithm till now.
And if yes would you be able to add support for it Later nex…
-
-
## Keyword: metric learning
### Sparse online relative similarity learning
- **Authors:** Dezhong Yao, Peilin Zhao, Chen Yu, Hai Jin, Bin Li
- **Subjects:** Machine Learning (cs.LG); Artificial Inte…
-
Similar to the Box-Cox transformation, the `asinh` or pseudolog transformation is a common transformation for reducing skewness and stabilizing variance. It's most often used for variables that are ro…
-
The active learning method that `dedupe` implements to learn a minimal set of predicates to block records can be very useful, particularly when the user has little prior knowledge on an appropriate se…