Program Objectives:

• Introduce core ML and AI principles
• Enable learners to build predictive and classification models
• Understand the ethical considerations in intelligent system design
• Familiarize participants with current trends and industry practices
• Motivate interdisciplinary research and innovation

What you will learn?

Day 1 – Foundations of Modern Machine Learning
● Evolution of Machine Learning: Classical to Intelligent Systems
● Supervised, Unsupervised & Self-Supervised Learning Techniques
● Structuring ML Pipelines: Data Preprocessing to Model Deployment
● Hands-On: Training your first ML model using scikit-learn on real-world data

Day 2 – Deep Learning & Transfer Learning in Action
● Understanding CNNs, RNNs, Transformers – Architectures that Matter
● Leveraging Transfer Learning with Pretrained Models (ResNet, BERT)
● Best Practices for Fine-Tuning and Customization
● Hands-On: Fine-tuning a transformer model for text classification using Hugging Face

Day 3 – ML Ethics, Interpretability & Applications
● Responsible AI: Fairness, Bias Mitigation, and Compliance
● Interpreting ML Decisions: SHAP, LIME, and XAI Tools
● Industry Use Cases: Healthcare, Finance, Smart Cities

● Hands-On: Interpreting model predictions using SHAP on a sensitive dataset