Applied Artificial Intelligence & Data Science
Semester-wise Duration – 60 Hrs/75 Hrs per ( 300 Hrs )
Program Objective:
This program aims to develop industry-ready professionals with strong skills in programming, data analysis, machine learning, deep learning, and generative AI. Through hands-on projects and real-world tools, students will gain the ability to build intelligent, data driven solutions across various domains.
Program Structure
Semester 3: Core Programming and Data Management
- Python Programming
- Relational Databases (RDBMS)
- Excel for Data Analysis
- Data modelling and analytics using Power Bi
- Exploratory Data Analysis (EDA) with Python
- Data Cleaning and Preprocessing
- Supervised Learning
- Unsupervised Learning
- Deep Learning Foundations
- Convolutional & Recurrent Neural Networks
- Model Deployment
- Natural Language Processing (NLP)
- Transformers and Language Models
- Generative AI Applications
- Experiential Project Based Learning
Program Outcomes
- Demonstrate proficiency in Python programming, data handling, and database management.
- Analyze and visualize complex datasets using Excel, Power BI, and Python-based tools.
- Apply supervised and unsupervised machine learning techniques to solve real-world problems.
- Design, train, and deploy deep learning models for image, text, and sequence data.
- Develop natural language processing and generative AI applications using modern AI frameworks.
Project streams
Core Programming and Data Visualization
- Student Grading System Using Python Functions
- Automated Sales Performance Dashboard in Excel
- Customer Segmentation with Grouped Insights
- Credit Risk Analysis Using Ensemble
- Multi-Class Image Classification with CNN
- License Plate Detection with OpenCV
Software & Frame work required
- Python & Jupyter Notebook
- MySQL
- MS Excel
- Anaconda / VS Code
- TensorFlow, Keras, PyTorch, OpenCV
- Streamlit, Gradio, Hugging Face
| Semester 3: Core Programming and Data Management (60 hours) | ||
|---|---|---|
| Python Programming - 30 hrs | ||
| Introduction to Python | Python Data types and Conditions | Control Statements |
| Python Functions | Default arguments | Functions with variable number of args |
| Scope of Variables | Global specifier | Working with multiple files |
| List and Tuple | List Methods | List Comprehension |
| Map and filter functions | String, Regular Expression | List comprehension with conditionals |
| Set and Dictionary | Exception Handling | File Handling |
| RDBMS with MySQL - 30 hrs | ||
| Introduction to databases and RDBMS | Database creation, concept of relation and working examples | Creating tables, Alter table operations & Key Constraints |
| Read, update and delete operations on tables | Querying tables: Select statement, examples and its variations | Filtering, Sorting, Predicates and working examples |
| Joins in SQL and working examples | Insert, Update, Delete operations and working examples | SQL set-based operations and data aggregation: Sub-queries in SQL |
| Semester 4: Data Analysis and Visualization for Insights (60 hours) | ||
| Excel for Data Analysis - 30 hrs | ||
| Introduction to MS-Excel | Fill Series, Flash Fill | Logical Functions – IF, AND, OR, NOT, IF Error |
| Text Functions | Date Functions | Statistical Functions |
| VLookup and H-Lookup | Index and Match Functions | Sorting and Filtering Data |
| Pivot Table | Data Validation | What-if Analysis |
| Charting techniques in Excel | Interactive dashboard creation | Data analytics project using Excel |
| Data Modelling and Analytics using Power BI - 30 hrs | ||
| Introduction to Power BI | Connecting to Data Sources | Power Query Editor |
| Data Modeling Concepts | Intermediate DAX | Creating Visuals and Dashboards |
| Bookmarks and Buttons | Maps and Custom Visuals | Advanced Charts and KPI Visuals |
| Semester 5: EDA & Machine Learning (60 hours) | ||
| Exploratory Data Analysis with Python – 30 hrs | ||
| NumPy Vectorization | Broadcasting | Slicing of Matrices |
| Filtering | Array Creation Functions | NumPy Functions across axis |
| Stacking of arrays | Matrix Calculation | Pandas Series |
| Data Cleaning | Handling Missing Data | Pandas Data frame |
| Selection Data (loc, iloc) | Filtering Data Frames | Working with Categorical Data |
| Grouping & Aggregation | Merging Data Frame (concat, merge) | Sorting Data Frames |
| Importing CSV Files | Importing Excel Files | Creating graphs using Matplotlib |
| Customizing Plots | Seaborn, Plotly | NumPy Vectorization |
| Broadcasting | ||
| Machine Learning – 30 hrs | ||
| Introduction to Machine Learning | Regression | Logistic regression |
| Supervised machine learning | Simple linear regression | Naïve Bayes Classification |
| Unsupervised machine learning | Multiple linear regression | Decision trees and its types |
| Train test split the data | Performance measure for regression | K Nearest Neighbour Classification |
| ML Workflow for project implementation | Classification and types | Performance Measure for Classification |
| Random Forest, Clustering and types | Evaluate clustering results, Elbow Plot | Optimizing regression models with forward elimination, grid search cv |
| Improving classification models with Ensemble modeling | Model evaluation strategies (KFold, Stratified KFold) | |
| Semester 6: Deep Learning and Model Deployment (60 hours) | ||
| Deep Learning – 50 hrs | ||
| What is Deep Learning | Performance measure for ANN | Building project based on CNN |
| Deep Learning Methods | Need for Hardware in Deep Learning | Need for Data augmentation |
| Deep Learning Application | Basics of image processing | Batch Normalization, dropout |
| Artificial Neural Network | OpenCV library | Object detection with CNN |
| Hidden Layers | Image reading, writing, enhancement | Object recognition with CNN |
| Activation Function | Edge detection, filtering, morphology | Forward and Backward propagation |
| CNN for computer vision | CNN architecture and its types | Tensorflow, PyTorch, Keras |
| Recurrent Neural Network (RNN) | Long- Short term Memory (LSTM) | Basic OpenCV Functions |
| Optical Character Recognition (OCR) | Automatic Number Plate Recognition (ANPR) | Developing an application using OpenCV |
| Model Deployment – 10 hrs | ||
| What is ML Model Deployment? | Batch vs Real-Time Inference | On-Prem vs Cloud vs Edge Deployment |
| Overview of ML Ops Lifecycle | Deployment Basics: Batch vs Real-Time Inference | CI/CD Concepts for ML |
| Deployment on Hugging Face, Streamlit, or Gradio | ||
| Semester 7: NLP and Generative AI (60 hours) | ||
| NLP for text processing – 40 hrs | ||
| Introduction to NLP | NLP: Areas of Application | Understanding the Text |
| Text Encoding | Word frequencies and stop words | Bag of words representation |
| Stemming and Lemmatization | TF-IDF representation | Canonicalisation |
| Phonetic Hashing | Spell Corrector | Point wise mutual Information |
| Gensim, Word2Vec | Word Embeddings | Bidirectional LSTM, Transformers |
| Generative AI – 20 hrs | ||
| Introduction to Gen AI | Representing correlation of words in numeric format | Topic modeling |
| Prompt Engineering | Application of Generative AI | Text Blob |
| Language Modeling | Building LLM Solutions | Embeddings, Vector DB |
| AI tools for productivity | Image based AI tools for Design and Creativity | Voice based AI Tools for Productivity |
| Experiential Project based Learning | ||
| An end-to-end Deep learning model development using scikit-learn, TensorFlow and real-world datasets with model deployment (DAV+ML+DL+NLP) | ||
