FDP on Explainable AI and MLOps with AWS
Type: Workshop
Explainable AI and MLOps with AWS
Building Trustworthy, Transparent & Deployable AI Systems
FACULTY-ORIENTED • HANDS-ON • INDUSTRY-RELEVANT • FUTURE-READY
Programme Fee
Regular Fee: ₹599
🎉 New Year Special Offer:
₹99 ONLY
A small step today can transform your teaching & research journey tomorrow. ⏳ Limited period offer for early registrations.
👉 Register now and start 2026 by upgrading your AI expertise.
How This FDP is Beneficial for Faculty
- Builds strong conceptual clarity in Explainable AI and MLOps
- Empowers faculty to confidently teach XAI in UG & PG programs
- Supports ethical and transparent AI research practices
- Enhances ability to guide AI, ML & data science student projects
- Introduces cloud-based deployment workflows used in industry
- Improves readiness for funded research and publications
- Provides reusable lab content and demonstration materials
Course Outcomes (COs)
- CO1: Apply Python programming for AI, XAI, and MLOps pipelines
- CO2: Build interpretable machine learning models
- CO3: Generate local and global explanations using LIME & SHAP
- CO4: Understand AWS-based MLOps workflows
- CO5: Deploy and monitor explainable AI applications
Certification
All participants will receive an
Official Certificate of Participation from Mevi Technologies LLP
upon successful completion of the FDP.
Day-Wise Programme Schedule
Day 1 – Python Foundations for AI & ML
- Role of Python in AI, Explainable AI, and MLOps
- Python execution flow and scripting practices
- Data types, variables, and control structures
- Functions and reusable code blocks
- NumPy arrays and vectorized operations
- Pandas DataFrames and Series
- Dataset loading from CSV and online sources
- Basic data preprocessing techniques
- Exploratory understanding of datasets
- Hands-on Python refresher exercises
Day 2 – Machine Learning Models & XAI Foundations
- Overview of the machine learning workflow
- Supervised vs unsupervised learning concepts
- Black-box models vs interpretable models
- Need for transparency and trust in AI systems
- Introduction to Explainable Artificial Intelligence (XAI)
- Global explanations vs local explanations
- Model-specific vs model-agnostic explanations
- Logistic Regression as an interpretable model
- Interpreting model coefficients
- Hands-on ML model building and explanation
Day 3 – Feature Importance, LIME & SHAP
- Understanding feature importance in ML models
- Permutation feature importance technique
- Limitations of traditional importance methods
- Introduction to local explanations
- Working principle of LIME
- Applying LIME to classification models
- Game-theoretic intuition behind SHAP
- Global and local SHAP explanations
- LIME vs SHAP – comparison and use cases
- Hands-on explanation of real predictions
Day 4 – MLOps Fundamentals with AWS
- Introduction to MLOps and ML lifecycle
- Challenges in deploying ML models
- Role of cloud platforms in MLOps
- Overview of AWS services for ML
- Using AWS S3 for dataset and model storage
- Model versioning and experiment tracking concepts
- Introduction to AWS SageMaker notebooks
- Basic training and experimentation workflow
- Monitoring and logging overview using CloudWatch
- Hands-on cloud-based ML workflow
Day 5 – Deploying Explainable AI Systems
- End-to-end AI system architecture
- Integrating explainability with deployed models
- Model deployment strategies on AWS
- Introduction to Streamlit for ML applications
- Building a simple Explainable AI interface
- Visualizing predictions with explanations
- Monitoring deployed models
- Responsible and ethical AI practices
- Industry and research use cases of XAI
- Live demonstration of explainable AI deployment