The framework currently optimises for greater accuracy. While accuracy is a widely used metric to assess the efficiency of training, it is not always desired. The framework should default to using accuracy as the training metric, but the user must be provided with a choice to use different optimisation.
Add support for the following optimisations that a user may specify.
Keep in mind that some parameters should be maximised while others should be minimised. An appropriate optimisation direction should be chosen respectively.
How can a user set the optimisation function
bc.optimiseFor("accuracy")The input can be taken in text form and must be case insensitive. Alternate more elegant solutions for choosing the optimisation time are encouraged.
Text labels to be used for each: accuracy, precision, recall, f1score, roc, auc, mse and mae
The framework currently optimises for greater accuracy. While accuracy is a widely used metric to assess the efficiency of training, it is not always desired. The framework should default to using accuracy as the training metric, but the user must be provided with a choice to use different optimisation.
Add support for the following optimisations that a user may specify.
Keep in mind that some parameters should be maximised while others should be minimised. An appropriate optimisation direction should be chosen respectively.
How can a user set the optimisation function
The input can be taken in text form and must be case insensitive. Alternate more elegant solutions for choosing the optimisation time are encouraged.
Text labels to be used for each:
accuracy,precision,recall,f1score,roc,auc,mseandmae