deep learning viva

Which of the following methods is not used for handling overfitting to the training set?

• Pooling

• Early stopping

• Data augumentation

• Dropout

which deep learning model is suitable for Name Entity Recognition(NER)

• RNN

• CNN

• MLP

• Both A & B

What is the purpose of using activation functions in a neural network?

• To introduce non-linearity in the network

• To reduce the computational complexity

• To increase the number of parameters

• To decrease the training time

Which of the following is a common loss function used in classification tasks?

• Mean Squared Error (MSE)

• Cross Entropy Loss

• Mean Absolute Error (MAE)

• Huber Loss

What is the purpose of batch normalization in deep learning models?

• To normalize the input data before feeding it to the network

• To speed up the training process by reducing internal covariate shift

• To increase the model complexity

• To prevent overfitting by regularizing the weights

What is the purpose of using regularization techniques in deep learning models?

• To increase the model complexity

• To prevent overfitting by penalizing large weights

• To speed up the training process by reducing internal covariate shift

• To normalize the input data before feeding it to the network

Which of the following is a common activation function used in deep learning models?

• Step function

• ReLU (Rectified Linear Unit)

• Tanh function

• Linear function

What is the purpose of the validation set in training a deep learning model?

• To train the model with additional data

• To evaluate the model's performance on unseen data

• To increase the complexity of the model

• To prevent overfitting during training

What is the purpose of using dropout in a neural network?

• To increase the model complexity

• To prevent overfitting by randomly dropping neurons during training

• To speed up the training process by reducing internal covariate shift

• To normalize the input data before feeding it to the network

Which of the following is a common optimizer used in training deep learning models?

• SGD (Stochastic Gradient Descent)

• Adam

• RMS PROP

• K-Means