Scribd
Upload
32 views2 pages

Deep Learning Assignment-2

Uploaded by

dpunj810
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
32 views2 pages

Deep Learning Assignment-2

Uploaded by

dpunj810
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

FACULTY OF ENGINEERING

SCHOOL OF INFORMATION, SECURITY AND DATA SCIENCE


B. Tech IT – VII-Sem
Session: JULY-NOV (2024)
DEEP LEARNING (IT4141)

EXTRA CLASS ASSIGNMENT- 2

Give the answer in True/False: (any two)


a) Activation function in Neural Network is non-linear in nature.
Q A1 b) McCulloch-pitts model have ability of learning.
c) Gradient Descent is a very popular classification algorithm.

a) If g is a hyperbolic tangent function, then g(z) = _____________


Q A2 b) PCA is a technique for _____________

Write Short Notes on the following: (any one)


a) Perceptron
Q A3
b) Role of Bias in Neural Network

Find the Principle Components for the following 2-D data:

(1,2), (3,3), (3,5), (5,4), (5,6), (6,5), (8,7), (9,8)


Q B1
If only the top eigen value is chosen, what will be the amount of information
preserved?
Q B2
Suppose we train the network with two points (0.5, 0.2) and (2.5, 0.9) with a single
neuron as shown in figure below:

1
The activation function used to train the network is given as f ( x )= and
−(w. x +b)
1+e
the loss function used is squared error loss function. With respect to this, using
gradient descent algorithm show how the values of ‘w’ and ‘b’ varies if the initial
setup is:
i) ‘w’ is chosen as ‘-ve’ and ‘b’ is -ve.
ii) ‘w’ is chosen +ve and ‘b’ is also chosen +ve.
iii) ‘w’ is chosen +ve and ‘b’ is chosen -ve.

Differentiate ReLU and Sigmoid activation function. Also write the mathematical
Q B3 expression and draw its rough graph. Why ReLU is preferred over Sigmoid?

What is the role of Backpropagation in Neural Network? Consider the below given
network with inputs A = 0.35 and B = 0.9 and find the output Y after 2 Iterations
where Learning Rate (η) is 0.1 and Target (Y) = 0.5.

Q C1

Assignment submission due date: 21/11/2024 in 2nd Extra class

You might also like