You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The purpose of this issue is to create a discussion whether having an EA parameterisation class would be a useful addition to stk, and, if so, the best approach to generate the API.
The goal of parameter optimisation is to identify the parameters of the EA that are best able to traverse the fitness landscape of molecules, identifying the global minima solution to the fitness function.
An implementation would need to include:
Methods to assess the performance of each EA run, i.e. amount of generations required to identify the global minima
Methods to iterate over parameter space, creating an instance of class EvolutionaryAlgorithm for each set of parameter options.
Any additional ideas would be welcome! @lukasturcani
The text was updated successfully, but these errors were encountered:
The purpose of this issue is to create a discussion whether having an EA parameterisation class would be a useful addition to
stk
, and, if so, the best approach to generate the API.The goal of parameter optimisation is to identify the parameters of the EA that are best able to traverse the fitness landscape of molecules, identifying the global minima solution to the fitness function.
An implementation would need to include:
EvolutionaryAlgorithm
for each set of parameter options.Any additional ideas would be welcome!
@lukasturcani
The text was updated successfully, but these errors were encountered: