Scribd
Upload
222 views2 pages

Assignment-1 Modeling and Simulation

The document contains 8 questions about concepts in machine learning and neural networks including perceptrons, loss functions, backpropagation, gradient descent, the effect of learning rate on neural network training, advantages of deep vs shallow neural networks, calculating outputs of a perceptron with given weights and inputs, and calculating outputs of a feedforward neural network with given weights, activation functions and inputs.

Uploaded by

Nishant Ty
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
222 views2 pages

Assignment-1 Modeling and Simulation

The document contains 8 questions about concepts in machine learning and neural networks including perceptrons, loss functions, backpropagation, gradient descent, the effect of learning rate on neural network training, advantages of deep vs shallow neural networks, calculating outputs of a perceptron with given weights and inputs, and calculating outputs of a feedforward neural network with given weights, activation functions and inputs.

Uploaded by

Nishant Ty
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Assignment-1

Modeling and Simulation

Q1. What do you mean by Perceptron?

Q2. Write the use of the loss function?

Q3. What do you mean by backpropagation?

Q4. Explain Gradient Descent?

Q5. How does the learning rate affect the training of the neural network?

Q6. Why are deep neural network preferred over shallow neural network?

Q7. Suppose we have a perceptron having weights corresponding to the three inputs have the
following values:

w1 = 2 ; w2 = −4; and w3 = 1

and the activation of the unit is given by the step-function:

φ(v) = 1 if v≥0 otherwise 0

Calculate the output value y of the given perceptron for each of the following input patterns:

       Pattern              P1               P2                 P3                P4


            X1              1                0         1                1
           X2              0                1         0                1
           X3              0                1         1                1

Q8. Consider a feed-forward Neural Network having 2 inputs(label -1 and label -2 )with fully
connected layers and we have 2 hidden layers:

Hidden layer-1: Nodes labeled as 3 and 4

Hidden layer-2: Nodes labeled as 5 and 6

A weight on the connection between nodes i and j is represented by wij, such as w24 is the weight on the
connection between nodes 2 and 4. The following lists contain all the weights values used in the given
network:

w13=−2, w35=1, w23 = 3, w45 = −1, w14 = 4, w36 = −1, w24=−1, w46=1

Each of the nodes 3, 4, 5, and 6 use the following activation function:

φ(v) = 1 if v≥0 otherwise 0


where v denotes the weighted sum of a node. Each of the input nodes (1 and 2) can only receive binary
values (either 0 or 1). Calculate the output of the network (y5 and y6) for the input pattern given by (node-1
and node-2 as 0, 0 respectively).

You might also like