Neural Networks Quiz

1. 1. In FeedForward ANN, information flow is _________.

• unidirectional

• bidirectional

• multidirectional

• All of the above

2. 2. What is perceptron?

• a single layer feed-forward neural network with pre-processing

• an auto-associative neural network

• a double layer auto-associative neural network

• a neural network that contains feedback

3. 3. What is back propagation?

• It is another name given to the curvy function in the perceptron

• It is the transmission of error back through the network to adjust the inputs

• It is the transmission of error back through the network to allow weights to be adjusted

• None of the Above

4. 4. Neural Networks are complex ______________ with many parameters.

• Linear Functions

• Nonlinear Functions

• Discrete Functions

• Exponential Functions

5 Arrange the following steps in the proper sequence for training a Neural Network

A. Repeat the process of multiple epochs until the network converges

B. Calculate the loss by comparing the predicted output to the actual output.

C. Perform the forward pass to compute the output.

D. Backpropagate the error to update the weights based on the loss.

E. Initialize the weights of the network.

• C - D - A - B - E

• E - C - B - D - A

• E- A - C - D - B

• A - C - B - D - E

6. 6. In which ANN, loops are allowed?

• FeedForward ANN

• FeedBack ANN

• Both A and B

• None of the Above

7. 7. What is a neuron in an ANN equivalent to in a biological neural network?

• Synapse

• Axon

• Brain

• Nerve cell

8. 8. What is the role of bias in a neural network?

• Normalize the input data

• Provide flexibility to the model by shifting the activation function

• Increase the number of neurons

• Prevent overfitting

9. 9. What does the term "epoch" in ANN training signify?

• A single iteration over the entire dataset

• A single data point processed by the network

• The number of layers in the network

• The initial weight setup

10. 10. Which of the following is a learning rate optimizer?

• Mean Squared Error

• Adam

• Sigmoid

• Softmax