Question 1
(a)
List out the key components found in a neural network.
3 Marks
(b)
Explain the concept of perceptron with a neat diagram.
4 Marks
(c)
What is overfitting? Expalin any three methods to prevent overfitting in neural networks.
7 Marks
Gujarat Technological UniversitySummer 2025 Examination
GTU 116AG01 Deep Learning and Neural Network Summer 2025 Paper Solution & PDF
B.E. · Computer Engineering · Semester 6 · Subject Code: 116AG01
Total Marks70 MarksExternal theory exam
Passing Marks23 Marks33% minimum cutoff
Exam Duration2.5 Hours10:30 AM – 1:00 PM
Paper Structure5 QuestionsWith internal OR choices
Question 2
(a)
Compare Artificial Neural Network with Biological Neural Network.
3 Marks
(b)
State difference between machine learning and deep learning
4 Marks
(c)
List and explain the various activation functions used in modeling of neural network.
7 Marks
OR OPTION
(c)
Explain Back propagation with its algorithm in Artificial Neural Network.
7 Marks
Question 3
(a)
Describe the concept of batch normalization.
3 Marks
(b)
What are different loss functions and their use case?
4 Marks
(c)
Draw and explain the architecture of RNN
7 Marks
OR OPTION
(a)
Calculate the output of the following neuron Y with the activation function as a sigmoid activation function.
3 Marks
(b)
Compare Single layer perceptron and Multi layer perceptron.
4 Marks
(c)
Draw and explain the architecture of LSTM
7 Marks
Question 4
(a)
Explain optimizers. Why optimizers are required?
3 Marks
(b)
Explain effect of learning rate in convergence of a neural network during training.
4 Marks
(c)
Draw and explain the architecture of Convolutional Neural Networks.
7 Marks
OR OPTION
(a)
Write applications of Deep Learning.
3 Marks
(b)
Explain the role of pooling layer in CNN. Find Feature map after applying Maxpool 2 x 2 with stride=1 on the following feature map. 12 1 5 1 6 9 0 0 7 5 1 8 0 3 6
4 Marks
(c)
Suppose 10000 patients get tested for flu; out of them 9000 are actually healthy and 1000 are actually sick. For the sick people, a test was positive for 620 and negative for 380. For healthy people, the same test was positive for 180 and negative for 8820. Construct a confusion matrix for the data and compute the accuracy, precision and recall for the data.
7 Marks
Question 5
(a)
Explain TensorFlow components.
3 Marks
(b)
Write the differences between eager execution and graph execution modes in TensorFlow.
4 Marks
(c)
Discuss steps to implement CNN using Keras.
7 Marks
OR OPTION
(a)
Write steps to train neural network model.
3 Marks
(b)
Explain types of tensors.
4 Marks
(c)
Explain steps to train RNN using TensorFlow.
7 Marks
College Exam Groups
Studying for Deep Learning and Neural Network?
Circulate this solved paper with KaTeX formulas and 1-click AI step solvers to your batchmates on WhatsApp or Telegram.
About this Examination Paper & Attribution
Official Gujarat Technological University (GTU) examination paper and step-by-step solutions for Deep Learning and Neural Network (Summer 2025, B.E. · Computer Engineering, Sem 6). Features complete 70-mark regular & remedial examination pattern, official marking distribution across all 5 questions, and direct 1-click official PDF download.
Transcribed for student exam preparation from Gujarat Technological University official examination archives. Questions, syllabus guidelines, and curriculum marking schemes remain the intellectual property of Gujarat Technological University.