Applied Artificial Intelligence and Machine Learning
Duration – 5 Day- FDP
Objectives
To enable faculty members to gain hands-on
exposure to core AI/ML concepts, tools, and
implementation techniques, empowering them to
guide students effectively and integrate data
science modules in engineering curriculum and
research.
Tools & Platforms
• Python
• JupyterNotebook
• GoogleColab
Pre-requisites
• Basic knowledge of Python programming
• Interest in data analysis and AI
• Familiarity with math concepts (mean, graph, etc.) is
helpful
Take away
• Access to datasets, notebooks, and curated resources
• Certification of Participation
• LMS Access (optional) for self-paced post-FDP learning
• Project assignment for faculty to work on after FDP
Day 2: Data Preprocessing using NumPy & Pandas
• NumPy essentials: arrays, operations, broadcasting
• Pandas for structured data handling
• Data loading, cleaning, filtering, and merging
• Handling missing values, encoding categorical data
• Feature scaling and normalization techniques
• Hands-On: Real-world dataset preprocessing using Pandas & NumPy
Day 3: Data Visualization for Analysis
• Importance of EDA (Exploratory Data Analysis)
• Visualization libraries: Matplotlib, Seaborn
• Univariate, Bivariate, and Multivariate Analysis
• Plot types: Histogram, Boxplot, Heatmaps, Pairplots
• Hands-On: Data visualization using Matplotlib, Pandas & Seaborn
• Data storytelling and pattern interpretation
Day 4: Supervised Learning – Regression & Classification
• Linear Regression and Polynomial Regression
• Logistic Regression and K-Nearest Neighbors (KNN)
• Decision Trees and Random Forests
• Train-Test Split, Cross Validation
• Hands-On: Classification & Regression using Scikit-learn
• Hyperparameter tuning with GridSearchCV
Day 5: Model Evaluation & Project Integration
• Model Evaluation Metrics:
• For Regression: MSE, RMSE, R² Score
• For Classification: Confusion Matrix, Accuracy, Precision, Recall, F1 Score, ROC-AUC
• Comparing model performance and selecting best model
• Best practices for model deployment & reproducibility
• Hands-On: Model comparison and evaluation with multiple algorithms
• Closing Session: Q&A, Resource sharing, Certification
