Deep Learning quiz 2

Batch normalization helps to prevent?

• Activation function to become too high or low

• The training speed to become too slow

• Both A and B

• None

Convolutional Neural Network is used in?

• Image classification

• Text Classification

• Computer vission

• All of the above

Which of the following Neural networks has a memory?

• 1D CNN

• 2D CNN

• LSTM

• None

In Neural Networks, which of the following causes the loss not to decrease faster?

• Stuck at a local minima

• High regularization parameter

• Slow learning rate

• All of the above

Which of the following activation function can not be used in the output layer of an image classification model?

• ReLu

• Softmax

• Sigmoid

• None

Suppose you are having a dataset from where you have to predict three classes. Then which of the following configuration should you use in the output layer?

• Activation function = softmax, loss function = cross entropy

• Activation function = sigmoid, loss function = cross entropy

• Activation function = softmax, loss function = mean squared error

• Activation function = sigmoid, loss function = mean squared error

Which of the following is true about bias?

• Bias is inherent in any predictive model

• Bias impacts the output of the neurons

• Both A and B

• None

Neural Networks can be used in?

• Regression problems

• Classification problems

• Clustering problems

• All of the above

In classification problem, which of the following activation function is most widely used in the output layer of the neural networks?

• Sigmoid function

• Hyperbolic function

• Rectifier function

• All of the above

Which of the following steps can be taken to prevent overfitting in Neural Networks?

• Dropout Neurons

• Early Stopping

• Batch Normalization

• All of the above