Evan Cofer

This is a pretty daunting task, and could be worthy of its own review paper. I'm not sure if we need to do something this extensive either, simply because many...

It may be worth pointing out programs like [NVIDIA's GPU grant program](https://developer.nvidia.com/academic_gpu_seeding). These can be really useful for a small project or for new labs interested in DL. I believe...

I'd love to work on this, but I think I am going to be MIA until I am finished with candidacy exams at the end of the month.

This is slightly similar to #49 , #35 , and #21

Indeed. In many cases however, sanity checks need to occur before hyperparameter optimization occurs.

Those all look like pretty relevant citations, and we should definitely keep them in mind as we draft. IIRC this discussion of testing & other software engineering best practices was...

Deep learning can also be good for combining structure and unstructured data (e.g. sequences and tabular covariates for each example), which IMO can be difficult to do with other paradigms....

@agitter I think they have slightly orthogonal goals. Whereas Kipoi eases maintainability/reuse of a user's implementations, Selene eases the implementation. As such, it may be more relevant to a discussion...

I would actually suggest trying out most of the "traditional methods" that are already implemented in scikit-learn or similar libraries. If you've tried out one of the scikit-learn models, it's...

An hour is sort of inconsequential, since using DL (esp after hyperparameter optimization) for those same tasks will take days. Maybe we should suggest that if the user isn't willing...