Absolute Free A00-225 Exam Practice for Comprehensive Preparation 

Activation function: Hyperbolic tangent (tanh), Error function: Cross-entropy

Activation function: Softmax, Error function: Mean squared error (MSE)

Activation function: Sigmoid, Error function: Cross-entropy

Activation function: ReLU (Rectified Linear Unit), Error function: Mean absolute error (MAE)

Use a normal distribution with an identity link function and adjust the model for overdispersion.

Use a Poisson distribution with a log link function, and apply a scale parameter to adjust for overdispersion.

Use a negative binomial distribution with a log link function.

Use a Poisson distribution with a square root link function and adjust the model for overdispersion.

Underfitting due to insufficient model complexity

Overfitting due to the model being too complex and capturing noise in the training data

Data leakage, where information from outside the training dataset has been incorrectly included

The new data has a different distribution than the training data, which is an instance of dataset shift

libname scoring odbc datasrc=mydatasource user=myusername password=mypassword;

libname scoring base 'mydatasource';

proc sql; connect to dbms(datasrc=mydatasource user=myusername password=mypassword); disconnect from dbms; quit;

filename mydblib odbc datasrc=mydatasource user=myusername password=mypassword;

SCORE DATA=validation OUT=scored_results OUTROC=roc_curve;

PROC LOGISTIC DATA=training; SCORE OUTROC=roc_curve; RUN;

PROC LOGISTIC DATA=training; SCORE DATA=validation OUTROC=roc_curve; RUN;

SCORE DATA=validation OUT=scored_results; MODEL OUTROC=roc_curve;