Unit-5
A) Describe the basic components of an artificial neural network, including
neurons, weights, and biases. How do these components interact to process
1 information?
B) How does the perceptron learning rule work? Explain the steps involved in
training a perceptron using gradient descent.
A) Design a two-layer perceptron network to implement the following logic
functions: a) X OR Yate b) X AND Y Gate.
2 B) What is a perceptron, and how does it function as a basic building block of
neural networks? Explain with an example
A) Describe the architecture of a multilayer neural network. How do input,
hidden, and output layers interact in the network?
3 B) Compare a single-layer perceptron with a multilayer perceptron.
(A) What are the limitations of artificial neural networks? Discuss issues such
as interpretability, data dependency, and computational cost.
4 B) What is an activation function in the context of artificial neural networks,
and why is it essential?
A) Explain the underlying learning theory, including how the perceptron
adjusts its weights based on input data to minimize error.
5
B) How is a perceptron different from a logistic regression model? Discuss
their similarities and differences.
A) What are the limitations of a single-layer perceptron in solving complex
problems like XOR classification?
6
B) What are deep neural networks, and how are they different from shallow
neural networks?
(A) Explain the concept of depth in a neural network. How does increasing the
depth of the network improve its ability to learn complex patterns?
(B) Given the following MLP architecture: Input layer: 3 neurons (labeled x 1,
x2, x3), Hidden layer: 2 neurons (labeled h 1 and h2), Output layer: 1 neuron
(labeled O). The weights from the input layer to the hidden layer are: w 11=0.5,
7 w12=−0.2, w13=0.3 for h1; w21=−0.4, w22=0.1, w23=0.7 for h2. The weights from
the hidden layer to the output layer are: w h1=0.6, wh2=−0.3. The biases are:
b1=0.1, b2=−0.2 for the hidden layer. bo=0.05 for the output neuron. Assume
the activation function is the sigmoid function.
Perform the feedforward operation in this MLP with the input vector
X=[1,0.5,0.2]. Calculate the output of the network, step by step.
A) Describe the step-by-step process of backpropagation in a multilayer
perceptron. How are errors propagated backward through the network?
8
B). Discuss the significance of the learning rate in backpropagation. How does
it affect the convergence of the model?
9 A) Explain the various types of artificial neural networks (ANNs), such as
feedforward, recurrent, and convolutional networks.
B) Explain the real-world applications of artificial neural networks (ANNs)
across various fields such as healthcare, finance, and image recognition.
A). How do weight initialization and optimization techniques impact the
performance of multilayer networks?
1
B) Describe the role of an activation function in a perceptron. Why is it
0
necessary, and what are some common activation functions used?