Closed drbenvincent closed 5 years ago
current results: We are getting some discrepant, and unexpected behaviours that deviate from the Matlab results. Todo:
Check that the Python model code is actually using the fixed value of alpha=2
and not in fact inferring it's values.
Actually, much of the discrepancy was because our prior on logk was waaaaay more broad than it should have been.
This issue is now resolved. We can do parameter recovery and parameter recovery sweeps and get some good outputs. Further improvements to our BAD approach will be dealt with elsewhere :)
For the record, the relatively poor performance of our approach was being caused by the heuristic (random_choice_dimension='DB'
). Once removed, the estimates for our approach are back to being very good.
In order to have faith that everything is working, we need to be able to perform some parameter recovery simulations.
The goal
Be able to reproduce figures like this
Basic functionality
get_simulated_response()
properlyTechnical debt to clear
get_simulated_response()
. We need to resolve this so that everything inbad
is entirely clueless about anythingdarc
related.Parameter recovery
/dev
folder as this is not really required or people, it's more for me to check stuff