Microsoft
DP-100 · Question #50
You are building a recurrent neural network to perform a binary classification. The training loss, validation loss, training accuracy, and validation accuracy of each training epoch has been…
The correct answer is B. The training loss decreases while the validation loss increases when training the model. An overfit model is one where performance on the train set is good and continues to improve, whereas performance on the validation set improves to a point and then begins to degrade. https://machinelearningmastery.com/diagnose-overfitting-underfitting-lstm-models/
Train and deploy models
Question
You are building a recurrent neural network to perform a binary classification. The training loss, validation loss, training accuracy, and validation accuracy of each training epoch has been provided. You need to identify whether the classification model is overfitted. Which of the following is correct?
Options
- AThe training loss stays constant and the validation loss stays on a constant value and close to the
- BThe training loss decreases while the validation loss increases when training the model.
- CThe training loss stays constant and the validation loss decreases when training the model.
- DThe training loss increases while the validation loss decreases when training the model.
How the community answered
(42 responses)- A2% (1)
- B93% (39)
- D5% (2)
Explanation
An overfit model is one where performance on the train set is good and continues to improve, whereas performance on the validation set improves to a point and then begins to degrade. https://machinelearningmastery.com/diagnose-overfitting-underfitting-lstm-models/
Topics
#Overfitting#Model Evaluation#Training Loss#Validation Loss
Community Discussion
No community discussion yet for this question.