Course Curriculam

Course Code: AIML303 Credit Units L T P/S SW AS/DS FW No. of PSDA Total Credit Unit
Course Level UG 3 0 2 0 0 0 0 4
Generative Artificial Intelligence (Generative
Course Title
AI)

Course
Description :

Course Objectives :

SN
Objectives
.
To equip students with a comprehensive understanding of Generative AI techniques, including GANs, Autoencoders, and RNNs. Enable them to
1 synthesize realistic data, generate creative content, and solve complex problems across diverse domains. Develop practical skills to harness the
power of AI-driven creativity and innovation.

Pre-Requisites : General

SN. Course Code Course Name

Course Contents / Syllabus :

SN. Module Descriptors / Topics Weightage

Module I: Introduction Basic introduction to Generative AI, Applications of Generative AI in various fields Perceptron and Multilayer
1 to Generative AI and Perceptron (MLP) Gradient Descent, Backpropagation algorithm. Loss functions Understanding Bias and 20.00
Fundamental Study Variance
Module II: Model
Parameters Methods to deal with overfitting issues. Optimizers (Momentum, Nesterov Accelerated Gradient, Adagrad,
2 Optimization and RMSprop, Adam) Convolution neural networks Understanding the architectural characteristics of deep CNNs 20.00
Convolution Neural Transfer Learning and Fine-tuning
Networks
Brief overview of Generative Models Introduction to Autoencoders and Variational Autoencoders Generative
Module III:
Adversarial Networks (GANs) for Realistic Data Synthesis Conditional Generative Models for Controlled Data
3 Generative 20.00
Generation Dealing with common issues like mode collapse and instability Use cases of GANs in image
Adversarial Networks
synthesis and data augmentation
Module IV: Use of
Recurrent Neural Networks (RNNs) Sequential models for solving Long-term dependency issues.
Recurrent Neural
4 Applications of RNNs in Generative AI: Text generation with RNNs. Music generation using RNNs. Speech 20.00
Networks in
synthesis and recognition
Generative AI
Module V: Attention ntroduction to attention mechanism, Use of attention in convolution neural network, Self-Attention, Spatial
5 Mechanism and and Channel Attention Transformer architecture, Vision Transformer, Transfer Learning with vision 20.00
Transformers transformer Applications of Vision Transformers (Image classification, Object detection)

Course Learning Outcomes :

SN. Course Learning Outcomes

Pedagogy for Course Delivery :

SN. Pedagogy Methods

The class will be taught using theory and applications. In addition to discussing real life applications, the course instructor will spend considerable
1 time in understanding the concept. The instructor will cover the ways to think innovatively liberally using thinking techniques. Delivery of course will
be covered using E-content based on 4-Quadrant approach.

Theory /VAC / Architecture Assessment (L,T & Self Work): 75.00 Max : 100

Attendance+CE+EE : 5+35+60

SN. Type Component Name Marks

1 Attendance 5.00
2 End Term Examination (OMR) 60.00
3 Internal CLASS TEST 15.00
4 Internal CLASS QUIZ 10.00
5 Internal HOME ASSIGNMENT 10.00

Lab/ Practical/ Studio/Arch. Studio/ Field Work Assessment : 25.00 Max : 100

Attendance+CE+EE : 5+35+60

SN. Type Component Name Marks

1 Attendance 5.00
2 External PRACTICAL 30.00
3 External VIVA VOCE 30.00
4 Internal PERFORMANCE 15.00
5 Internal VIVA VOCE 10.00
6 Internal Lab record including Attendance,Ethics,Precautions,Interactions 10.00

Lab/ Practical details, if applicable :

SN
Lab / Practical Details
.
1.Build an Artificial Neural Network to implement Binary Classification task using the Back-propagation algorithm and test the same using appropriate
1
data sets.
2.Build an Artificial Neural Network to implement Multi-Class Classification task using the Back-propagation algorithm and test the same using
2
appropriate data sets.
3.Design a CNN architecture to implement the image classification task over an image dataset. Perform the Hyper-parameter tuning and record the
3
results.
4 4.Implement an image classification task using pre-trained models like AlexNet, VGGNet, InceptionNet and ResNet and compare the results.
5 5.Implement Autoencoder architecture for image segmentation task.
6 Implement GAN architecture on MNIST dataset to recognize the handwritten digits
7.Develop a GAN-based model that can translate images from one domain to another, such as converting sketches to realistic images or
7
transforming day to night scenes.
8 8.To build a recurrent neural network (RNN) to generate new musical compositions based on existing music datasets.
9 9.Implement Vision Transformer architecture for image classification task.
10 10.Implement convolutional vision transformer for image classification task.

List of Professional skill development activities :

No.of PSDA : 0
SN. PSDA Point

Text & References :

SN. Type Title/Name Description ISBN/ URL

1."Deep Learning" by Ian Goodfellow,
1 Book Yoshua Bengio, and Aaron Courville,
published by MIT Press in 2
2."Hands-On Machine Learning with Scikit-
2 Book Learn, Keras, and TensorFlow" by Aurélien
Géron, published
3.Deep Learning with Python" by François
3 Book Chollet, published by Manning Publications
in 2018.
4."Python Machine Learning" by Sebastian
4 Book Raschka and Vahid Mirjalili, published by
Packt Publishing
"Applied Deep Learning: A Case-Based
5 Book Approach to Understanding Deep Neural
Networks" by Umberto Mich
6.Deep Learning for Computer Vision" by
6 Book Rajalingappaa Shanmugamani, published
by Packt Publishing in
7."Reinforcement Learning: An
7 Book Introduction" by Richard S. Sutton and
Andrew G. Barto, published by T
8."Deep Learning Illustrated" by Jon Krohn,
8 Book published by Addison-Wesley Professional
in 2019.
9."Hands-On Deep Learning for Images
9 Book with TensorFlow" by Will Ballard, Luis
Capelo, and Ankit Jain,