Minor in Artificial Intelligence 2024

Minor in Artificial Intelligence -

Offered by Vizuara
Program Duration: 2 Years

Key highlights

150 hours of Learning

Live Lectures by IIT, MIT (USA), Purdue PhDs
5-day Campus Immersion

Program Overview
The Minor in Artificial Intelligence program offered by Vizuara is designed to provide a comprehensive
introduction to the field of AI. This 2 year program is curated to offer foundational knowledge and
advanced skills through live lectures delivered by esteemed PhDs from IIT and MIT. The program also
includes a 5-day campus immersion for hands-on experience.

Certificate
Upon successful completion, participants will be awarded a Minor in Artificial Intelligence certificate
from Vizuara and SPIT.

Program Structure
The program is divided into four semesters, each focusing on different aspects of AI and ML.

Minor in Artificial Intelligence

Semester No. Course L T P O E C
4 Foundations in AI and ML 3 0 0 3 6 3
5 Machine Learning and Deep Learning Mastery* 3 0 2 5 9 4
6 NLP and CV Mastery, Capstone Project 3 0 0 5 8 3
Large Language Models Theory and Deployment, Capstone
7 3 0 2 5 9 4
Project*

Table 1: Vizuara Minor in Artificial Intelligence program structure

*The practicals will be covered through the homework assignments itself.

Program Benefits
• Minor in AI certificate upon completion
• Live interaction with PhD instructors from IIT, MIT
• Hands-on learning through labs and projects
• Access to campus immersion program for practical exposure
• Networking opportunities with industry professionals

1
 Minor in Artificial Intelligence 2024

Detailed description of each course

Semester I, Course I: Foundations in AI and ML (3 credits)

Module No. Unit No. Topics Ref. Hours

Title: Mathematics Foundations
1.1 Linear Algebra: Vectors, Matrices, Eigenvalues, Eigenvec- 1,2 4
1 tors
1.2 Probability and Statistics: Bayes Theorem, Distributions, 1,2 4
Hypothesis Testing
1.3 Calculus: Differentiation, Integration, Partial Derivatives 1,2 3
Title: Programming Foundations
2.1 Python Programming: Data Types, Control Flow, Func- 3 4
2
tions
2.2 Libraries for AI: NumPy, Pandas, Matplotlib 3 4
Title: Introduction to Optimization
3.1 Optimization Algorithms: Gradient Descent, Stochastic 1,4 4
3
Gradient Descent, Adam
3.2 Convex and Non-convex Optimization: Introduction and 1,4 3
Examples
Title: The AI Landscape: 2020-2030
4.1 Overview of Machine Learning and Deep Learning: Super- 1,4 4
4
vised, Unsupervised Learning
4.2 Generative AI: GANs, VAEs, and Future Trends in AI Re- 1,4 4
search
Title: Data Storytelling and Visualization
5.1 Data Manipulation: Cleaning, Filtering, and Transforming 4 4
5
Data using Pandas
5.2 Data Visualization: Creating Effective Visualizations with 4 4
Matplotlib and Seaborn

Table 2: Module Breakdown for Foundations in AI and ML Course

Course Outcomes (CO): At the End of the course students will be able to
CO 1 Understand fundamental concepts of Linear Algebra including vectors, matri-
ces, eigenvalues, and eigenvectors.
CO 2 Apply Probability and Statistics concepts like Bayes Theorem, distributions,
and hypothesis testing in AI models.
CO 3 Utilize Calculus methods including differentiation, integration, and partial
derivatives to solve problems in AI/ML.
CO 4 Develop Python programming skills including data types, control flow, and
functions for AI-related applications.
CO 5 Analyze data manipulation techniques using Pandas and data visualization
with Matplotlib and Seaborn.

Table 3: Course Outcomes for Foundations in AI and ML

Pre-requisite Courses, if any

Basic understanding of 11th grade and 12th grade mathematics

Table 4: Prerequisites

2
 Minor in Artificial Intelligence 2024

Sr. No. Title Creators Publisher

1 Grant Sanderson videos and notes Grant Sanderson Youtube
2 Introduction to Linear Algebra Gilbert Strang MIT Press
3 Introduction to Python Ana Bell MIT Press
4 Introduction to AI and ML Dr. Raj Dandekar, Dr. Vizuara AI Labs org
Rajat Dandekar, Dr.
Sreedath Panat

Table 5: Reference Materials

3
 Minor in Artificial Intelligence 2024

Semester II, Course II: Machine Learning and Deep Learning Mastery

Module No. Unit No. Topics Ref. Hours

Title: Machine Learning Techniques
1.1 Supervised Learning: Regression, Classification (Logistic 1,2 6
1 Regression, SVM)
1.2 Unsupervised Learning: Clustering (K-Means, DBSCAN) 1,2 3
1.3 Decision Trees and Random Forests 1,2 3
Title: Deep Learning Techniques
2.1 Build a neural network from scratch: Forward pass 1,2 5
2
2.2 Build a neural network from scratch: Backward pass 1,2 5
2.3 Assemble and train the entire neural network 1,2 2
2.4 Testing the entire neural network 1,2 2
Title: Big Data Techniques
3 3.1 Handling Large Datasets: Data Preprocessing, Data Wran- 1,2 6
gling, Feature Selection
Title: Machine Learning - Deep Learning Lab
4 4.1 Hands-on Projects: Real-life datasets for ML/DL applica- 1,2 5
tions
Title: Projects to Research Papers
5 5.1 Converting Projects into Research Papers: Writing impact- 1,2 5
ful papers

Table 6: Module Breakdown for Machine Learning and Deep Learning Mastery Course

Course Objectives (CO): At the end of the course, students will be able to
CO 1 Understand Supervised Learning techniques such as Regression, Classification
(Logistic Regression, SVM).
CO 2 Apply Unsupervised Learning methods like Clustering (K-Means, DBSCAN).
CO 3 Utilize Decision Trees and Random Forests for problem-solving.
CO 4 Build neural networks from scratch, understanding the forward and backward
passes.
CO 5 Handle large datasets through preprocessing, data wrangling, and feature se-
lection.
CO 6 Execute hands-on projects using real-life datasets for ML/DL applications.
CO 7 Convert machine learning and deep learning projects into research papers, fo-
cusing on writing impactful papers.

Table 7: Course Objectives for Machine Learning and Deep Learning Techniques

Pre-requisite Courses, if any

Course 1 on Foundations needs to be completed. Understanding of Python
Programming, Linear Algebra, Statistics and Calculus

Table 8: Prerequisites

4
 Minor in Artificial Intelligence 2024

Sr. No. Title Creators Publisher

1 Introduction to ML and DL Dr. Raj Dandekar, Dr. Vizuara AI Labs org
Rajat Dandekar, Dr.
Sreedath Panat
2 Deep Learning Ian Goodfellow, Yoshua MIT Press
Bengio, and Aaron
Courville
3 Hands-On Machine Learning with Geron Aurelien O’Reilly
Scikit-Learn and TensorFlow

Table 9: Reference Materials

5
 Minor in Artificial Intelligence 2024

Semester III, Course III: Natural Language Processing (NLP) and Computer
Vision (CV) Mastery, Capstone Project (4 credits)

Module No. Unit No. Topics Ref. Hours

Title: Natural Language Processing (NLP) Techniques
1.1 Introduction to NLP: Text Preprocessing, Tokenization, 1,2 6
1 and Parsing
1.2 NLP Techniques: N-grams, TF-IDF, Word Embeddings 1,2 6
(Word2Vec, GloVe)
1.3 Language Models: RNN, LSTM, Transformer 1,2 6
Title: Computer Vision (CV) Techniques
2.1 Introduction to Computer Vision: Image Preprocessing, 1 6
2 Feature Extraction
2.2 CV Techniques: CNN, Transfer Learning, Object Detection 1 6
2.3 Advanced Topics: GANs for Image Generation, Vision 1 6
Transformers
Title: NLP & CV Lab
3 3.1 Hands-on Lab: Implementing NLP and CV Models using 1 6
TensorFlow, Keras
Title: Capstone Project
4 4.1 Industrial Capstone Project: Implementing a Real-world 1 6
NLP or CV Project

Table 10: Module Breakdown for NLP and CV Mastery with Capstone Project

Course Objectives (CO): At the end of the course, students will be able to
CO 1 Understand basic Natural Language Processing (NLP) techniques, including
text preprocessing, tokenization, and parsing.
CO 2 Apply various NLP techniques like N-grams, TF-IDF, and Word Embeddings
(Word2Vec, GloVe).
CO 3 Explore advanced language models such as RNNs, LSTMs, and Transformers
for NLP applications.
CO 4 Understand fundamental Computer Vision (CV) techniques, including image
preprocessing and feature extraction.
CO 5 Apply advanced CV techniques like Convolutional Neural Networks (CNN),
Transfer Learning, and Object Detection.
CO 6 Explore cutting-edge topics in CV like Generative Adversarial Networks
(GANs) and Vision Transformers.
CO 7 Implement NLP and CV models using TensorFlow and Keras in hands-on lab
projects.
CO 8 Work on an industrial capstone project involving real-world NLP or CV appli-
cations.

Table 11: Course Objectives for Natural Language Processing (NLP) and Computer Vision (CV) Mas-
tery, Capstone Project

Pre-requisite Courses, if any

Course 1 on Foundations and Course 2 on ML/DL Mastery needs to be com-
pleted

Table 12: Prerequisites

6
 Minor in Artificial Intelligence 2024

Sr. No. Title Creators Publisher

1 Introduction to NLP and CV Dr. Raj Dandekar, Dr. Vizuara AI Labs org
Rajat Dandekar, Dr.
Sreedath Panat
2 Natural Language Processing with Steven Bird O’Reilly
Python
3 Jay Alammar blogs Jay Alammar Github, Youtube

Table 13: Reference Materials

7
 Minor in Artificial Intelligence 2024

Semester IV, Course IV: Large Language Models Theory and Deployment,
Capstone Project (4 credits)

Module No. Unit No. Topics Ref. Hours

Title: Build your own GPT from Scratch
1.1 Introduction to LLMs: Understanding Transformer Archi- 1,2, 3 8
1 tecture
1.2 Pre-training Techniques for LLMs: Masked Language Mod- 1,2, 3 6
eling, Causal Language Modeling
1.3 Fine-tuning LLMs: Adapting Pre-trained Models to Spe- 1,2, 3 6
cific Tasks
Title: LLM Deployment
2.1 Model Deployment Basics: Infrastructure, Scalability, and 2 6
2
Latency Reduction
2.2 Deploying LLMs on Cloud: AWS, Google Cloud, and Azure 2 4
Title: LLM Practical Deployment Lab
3 3.1 Hands-on Lab: Deploying an LLM for Real-time Applica- 1, 2 6
tions
3.1 Understanding RAG for supplementing LLM with addi- 1, 2 6
3
tional information
Title: Capstone Project
4 4.1 Industrial Capstone Project: Deploying an LLM in a Real- 1 6
world Application

Table 14: Module Breakdown for Large Language Models Theory and Deployment with Capstone Project

Course Objectives (CO): At the end of the course, students will be able to
CO 1 Understand the basics of Large Language Models (LLMs) and the Transformer
architecture.
CO 2 Apply pre-training techniques for LLMs, including Masked Language Modeling
and Causal Language Modeling.
CO 3 Fine-tune pre-trained LLMs for specific tasks, adapting them to diverse appli-
cations.
CO 4 Learn the fundamentals of model deployment, covering infrastructure, scala-
bility, and latency reduction.
CO 5 Deploy LLMs on popular cloud platforms like AWS, Google Cloud, and Azure.
CO 6 Gain hands-on experience in deploying an LLM for real-time applications in
the lab.
CO 7 Understand Retrieval-Augmented Generation (RAG) techniques to supplement
LLMs with additional information.
CO 8 Work on an industrial capstone project, deploying an LLM in a real-world
application setting.

Table 15: Course Objectives for Build Your Own GPT from Scratch

Pre-requisite Courses, if any

Course 1 on Foundations, Course 2 on ML/DL Mastery and Course 3 on
NLP/CV master needs to be completed

Table 16: Prerequisites

8
 Minor in Artificial Intelligence 2024

Sr. No. Title Creators Publisher

1 Introduction to LLMs Dr. Raj Dandekar, Dr. Vizuara AI Labs org
Rajat Dandekar, Dr.
Sreedath Panat
2 Hands-On Large Language Models Jay Alammar, Maarten O’Reilly
Grootendorst
3 Grant Sanderson videos and notes Grant Sanderson Youtube

Table 17: Reference Materials