Empowering Future Innovators with AI & ML — Learn from IIT Kharagpur Experts – Rkmvivekatirtha

$Blue Grey Modern Math Club Logo (1)$

0%

Loading ...

Course Content

Module1:Foundations of Machine Learning (6 Hours)
1. Introduction to Al and ML (1 Hour) Al vs ML vs DL vs Generative Al History and evolution of AI/ML ML lifecycle in industry Roles and expectations of entry-level ML engineers Industry use cases across domains Lab / Assignment Python environment setup Git and project structure Explore and understand a real-world dataset

2. ML Fundamentals and Data Pipeline (5 Hours)
Theory: 3 Hours | Lab: 2 Hours Supervised, unsupervised, and reinforcement learning (overview) Train, validation, and test splits Data preprocessing: Handling missing values Ο Encoding categorical variables Ο Feature scaling Feature engineering techniques Evaluation metrics: Ο Regression metrics Classification metrics Bias-variance tradeoff Lab / Assignment Build a complete preprocessing and modeling pipeline using scikit-learn

Module 2: Core Machine Learning Algorithms (14 Hours)
3. Regression Models (4 Hours) Theory: 2 Hours | Lab: 2 Hours Linear regression Polynomial regression Regularization techniques: L1 (Lasso) L2 (Ridge) ElasticNet Model interpretation and feature importance Lab / Assignment House price or sales prediction using regression models

4. Classification Models (6 Hours)
Theory: 3 Hours | Lab: 3 Hours Logistic regression Decision trees Random forests Gradient boosting (XGBoost) Support Vector Machines Handling imbalanced datasets - SMOTE Lab / Assignment Customer churn, fraud detection, or risk classification problem Model comparison and evaluation

5. Unsupervised Learning and Dimensionality Reduction (4 Hours)
Theory: 2 Hours | Lab: 2 Hours K-Means clustering Hierarchical clustering DBSCAN Principal Component Analysis (PCA) t-SNE for visualization Lab / Assignment Customer or user segmentation using clustering and PCA

Module 3: Guided Real-World ML Project (5 Hours)
6. Project Phase 1: Classical Machine Learning - Healthcare Readmission Risk Prediction Guided Lab: 5 Hours Problem formulation Baseline model development Feature engineering Model evaluation and validation Error analysis Introductory model explainability (SHAP) Outcome Well-documented classical ML solution with measurable improvements

Module 4: Deep Learning Fundamentals (8 Hours)
7. Neural Networks and MLPS (3 Hours) Theory: 1.5 Hours | Lab: 1.5 Hours Neural network fundamentals Activation functions Loss functions and optimization Overfitting and regularization techniques Lab / Assignment Implement a multi-layer perceptron using PyTorch or TensorFlow

8. Convolutional Neural Networks and Transfer Learning (3 Hours)
Theory: 1.5 Hours | Lab: 1.5 Hours CNN architecture and components Transfer learning concepts Fine-tuning pretrained models Lab / Assignment Image classification using a pretrained CNN model

9. Sequence Models (2 Hours)
Theory: 1.5 Hours | Lab: 0.5 Hour Recurrent Neural Networks and LSTMs Limitations of RNNS Motivation for transformers Lab / Assignment Simple sequence modeling example (text or time series)

Module 5: Natural Language Processing and Large Language Models (7 Hours)
10. NLP Foundations (3 Hours) Theory: 1.5 Hours | Lab: 1.5 Hours Text preprocessing techniques Tokenization methods Word embeddings Transformer architecture intuition Lab / Assignment Text classification using traditional and embedding-based approaches

11. Large Language Models and Generative AI (4 Hours)
Theory: 1.5 Hours | Lab: 2.5 Hours Prompt engineering techniques Using Hugging Face models for inference Fine-tuning vs parameter-efficient methods Retrieval-Augmented Generation (RAG) Using LLM APIs (OpenAI or open-source models) Lab / Assignment Build an LLM-powered application such as Q&A or summarization

Module 6: MLOps Essentials (6 Hours)
12. Model Evaluation, Tracking, and Deployment Theory: 2 Hours | Lab: 4 Hours Cross-validation strategies Hyperparameter tuning Experiment tracking with MLflow Model versioning and artifact management Model serving using FastAPI Docker basics for ML applications Model monitoring and data drift concepts Lab / Assignment Deploy a trained ML model as a REST API Track experiments and model versions

Module 7: Review (4 Hours)
13. Model Evaluation, Tracking, and Deployment Key Algorithm Review Linear and Logistic Regression Decision Trees and Random Forests Gradient Boosting K-Means Clustering and PCA Neural Networks (MLP) CNNs (high-level) Transformer and LLM pipeline (high-level) Choosing the right algorithm for a given problem Comparing classical ML vs deep learning approaches Assessment and Feedback Short assessment covering: Algorithm selection and reasoning Ο Evaluation metrics Practical ML workflow understanding Review of lab assignments and guided project work Individual feedback on strengths, gaps, and capstone readiness

A course by

RV

RKM Viveka Tirtha

Student Ratings & Reviews

No Review Yet

No Review Yet

Price:
Original price was: ₹30,500.00.Current price is: ₹29,500.00.
Instructor:RKM Viveka Tirtha
Lessons:0
Students:0
Level:All Levels