William La Cava

allow users to choose to tune the hyperparameters of the ML method they choose, rather than choosing parameters themselves.

additional termination conditions

1

As mentioned in #124, we want the user to be able to specify additional termination conditions for the recommender, besides a set number of analyses. Other ways the recommender could...

when loading a knowledgebase, check the result ML/P combos against projects.json (get_all_ml_p() in api_utils.py) and abort if there are invalid options. (incorporate valid_param_combo() and ml_p_opts checks from reformat_sklean_results.ipynb)

re-structure code as module so it can be distributed as a package.

put scores in database for persistence

1

recommender should have method to store scores in the database for persistence. probably makes sense to use pyMongo for this.

replace point mutation with a length-based probability of mutation at each node.

add operators that re-encode input SNPs based on different encodings. include (add, dom, rec, het, sub-add, super-add). Need to resolve how underlying data would be represented; maybe assume the input...

add size mediated parent selection for lexicase survival

1

include option to mediate lexicase survival via size of programs for each selection event.

I'm getting low utilization of the GPU using the tensorflow evaluation strategy. There are a few things to try: - use [this method](https://github.com/tensorflow/tensorflow/issues/1824#issuecomment-225754659) to profile tensorflow and see where the...

implement truncation selection based on feature scores. if none, use estimated fitness