Chris Swierczewski comments

Results 4 comments of


                                            Chris Swierczewski

Sagemaker LDA topic model - how to access the params of the trained model? Also is there a simple way to capture coherence

> Duplicated from [this StackOverflow response](https://stackoverflow.com/a/54952503/645494). [This SageMaker notebook](https://github.com/awslabs/amazon-sagemaker-examples/blob/master/scientific_details_of_algorithms/lda_topic_modeling/LDA-Science.ipynb), which dives into the scientific details of LDA, also demonstrates how to inspect the model artifacts. Specifically, how to obtain the...

Add support for batch training

First possibly-related question: in the context of using XGBModule as, say, the first layer of a network, how does XGB sample weighting jive with network training? In XGBModule the main...

Add support for batch training

> I think there are enough compelling cases that extend xgb/lgb, that my plan right now is to focus on those, and this does not require the mini-batching since you'd...

Add support for batch training

> It sounds like you may have this working already but just in case, a basic version of the network you are interested in is here: I did indeed get...