Unit 5-1
Unit 5-1
Unit 5-1
11. Which of the following is an advantage of using ANNs for pattern recognition?
a) Ability to learn from large amounts of data
b) Robustness to noise and variations in input
c) Scalability to handle complex tasks
d) All of the above
13. Which type of ANN architecture is commonly used for image classification tasks?
a) Convolutional Neural Network (CNN)
b) Recurrent Neural Network (RNN)
c) Radial Basis Function Network (RBFN)
d) Multilayer Perceptron (MLP)
Answer: a) To set the initial values of the weights and biases in the network
15. Which activation function is commonly used in the output layer for binary classification
in ANNs?
a) Sigmoid
b) ReLU (Rectified Linear Unit)
c) Tanh (Hyperbolic Tangent)
d) Softmax
Answer: a) Sigmoid
Answer: a) To adjust the learning rate during training for better convergence
19. Which of the following techniques can be used to prevent overfitting in ANN training?
a) Dropout regularization
b) L1 and L2 regularization
c) Early stopping
d) All of the above
21. Which type of ANN architecture is commonly used for reinforcement learning tasks?
a) Deep Q-Network (DQN)
b) Generative Adversarial Network (GAN)
c) Boltzmann Machine
d) Autoencoder
22. What is the purpose of momentum in the optimization algorithm used for ANN training?
a) To accelerate the convergence of the algorithm
b) To prevent overfitting by regularizing the model
c) To adjust the learning rate during training
d) None of the above
24. Which type of ANN architecture is commonly used for natural language processing
tasks?
a) Recurrent Neural Network (RNN)
b) Convolutional Neural Network (CNN)
c) Multilayer Perceptron (MLP)
d) Radial Basis Function Network (RBFN)
Answer: a) To update the model's weights and biases after processing a subset of the training
data
26. What is the main advantage of using deep neural networks compared to shallow neural
networks?
a) Ability to learn hierarchical representations of data
b) Faster convergence during training
c) Lower computational complexity
d) None of the above