Answer-first summary for fast verification
Answer: The training loss decreases while the validation loss increases when training the model.
Overfitting occurs when a model learns the training data too well, including noise and details, but fails to generalize to unseen data. This is characterized by decreasing training loss (indicating good performance on training data) and increasing validation loss (indicating poor generalization to validation data). Option B correctly describes this pattern. The community discussion strongly supports B with 100% consensus and upvoted comments explaining that overfitting shows high training accuracy (low training loss) and low validation accuracy (high validation loss). Other options are incorrect: A suggests no learning or perfect generalization (unlikely), C suggests validation improves while training stagnates (contradicts overfitting), and D suggests training worsens while validation improves (opposite of overfitting).
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are building a recurrent neural network for binary classification. After reviewing the training loss, validation loss, training accuracy, and validation accuracy for each epoch, you need to determine if the model is overfitted. Which of the following statements is correct?
A
The training loss stays constant and the validation loss stays on a constant value and close to the training loss value when training the model.
B
The training loss decreases while the validation loss increases when training the model.
C
The training loss stays constant and the validation loss decreases when training the model.
D
The training loss increases while the validation loss decreases when training the model.
No comments yet.