DL Quiz-1 6CSM1 batch-2

 

What is the main goal of deep learning?

• Unsupervised learning

• Feature extraction

• Training neural networks to learn from data and make predictions

• Reinforcement learning

Which type of neural network architecture is primarily used for image processing tasks?

• Recurrent Neural Networks (RNNs)
  
  

• Convolutional Neural Networks (CNNs)

• Deep Belief Networks (DBNs)

• Autoencoders

What is backpropagation in the context of deep learning?

• A method for forward pass in neural networks
  
  

• A method for feature selection

• A technique to prevent overfitting

• A method for adjusting weights based on prediction errors

What is the vanishing gradient problem in deep learning?

• 
  A situation where gradients approach zero, leading to slow or stalled learning
  

• A challenge in parallelizing deep learning algorithms

• A phenomenon where gradients become too large during training

• A problem caused by a small learning rate

Which deep learning architecture is well-suited for processing sequential data like natural language?

• CNN
  

• RNN

• LSTM

• GAN

How many waves of development of Deep Learning are there?

• 1

• 2

• 3

• 4

Which of the below regularization technique tracks the validation loss

• Dropout
  

• Early stopping

• L1 regularization

• L2 regularization

Which deep learning framework is known for its ease of use and good community support?

• 
  PyTorch
  

• TensorFlow

• Caffe

• Keras

Which activation function is most commonly used in hidden layers of a neural network?

• Sigmoid

• Tanh

• Softmax

• ReLU

Which of the following technique is suitable for building a robust deep learning model?

• L1 regularization

• L2 Regularization

• Batch Normalization

• Gradient Clipping