Quiz-2

How does a Perceptron differ from a Neuron in ANN

• Perceptrons and Neurons are identical terms
  

• Neurons are simpler computational units compared to Perceptrons

• Perceptrons are biological, while Neurons are artificial

• There is no difference; both terms can be used interchangeably

In a Perceptron, what are weights and biases used for?

• To increase the computational complexity of the model

• To adjust the learning rate during training

• To control the activation function of the perceptron

• To modulate the strength of input signals and introduce an offset

What is the role of an activation function in a neural network?

• To initialize the weights of the network

• To control the learning rate during training

• To introduce non-linearity into the model

• To adjust the bias terms in each layer

How does the Vanishing Gradient Problem affect the training of deep neural networks?

• It accelerates the convergence of the model

• It leads to faster training times

• It makes training slow and difficult for deeper layers

• It has no impact on the training process

What is the role of the input layer in a neural network?

• To make predictions

• To process incoming data and pass it to the output layer

• To adjust weights during training

• To provide feedback during backpropagation

What is the primary use of CNNs in machine learning?

• Natural Language Processing
  

• Image and Video Recognition

• Time Series Forecasting

• Reinforcement Learning

What is the role of pooling layers in a CNN?

• To flatten the input data

• To introduce non-linearity
  

• To calculate gradients during backpropagation

• To reduce the spatial dimensions of the input data

During Forward Propagation, what is passed through the neural network from the input layer to the output layer?

• Gradients
  

• Weights and biases

• Input data

• Activation functions

How does the visualization of the Sigmoid activation function typically appear?

• As a straight line

• As an inverted "U" shape

• As a step function

• As an exponential curve

If a model has an accuracy of 90%, what does this imply?

• The model is highly accurate and performs well in all scenarios
  

• The model is making incorrect predictions 10% of the time

• The model is likely overfitting the training data

• The model is underfitting the training data