Detailed Syllabus & Weekly Breakdown

Module 1: Python for Data Science & Math Foundations (Weeks 1–6)

• Week 1-2: Core Python, Pandas, NumPy for Data Manipulation
• Week 3-4: Applied Linear Algebra & Calculus for ML
• Week 5-6: Probability, Statistics & Data Visualization (Seaborn)

Module 2: Supervised & Unsupervised Learning (Weeks 7–12)

• Week 7-8: Linear & Logistic Regression, SVMs
• Week 9-10: Decision Trees, Random Forests, Ensemble Methods (XGBoost)
• Week 11-12: K-Means Clustering, PCA, Hyperparameter Tuning

Module 3: Deep Learning & Neural Networks (Weeks 13–18)

• Week 13-14: Artificial Neural Networks (ANN), Backpropagation, Activation Functions
• Week 15-16: PyTorch & TensorFlow framework introduction
• Week 17-18: Optimization Algorithms (Adam, SGD), Dropout, Regularization

Module 4: NLP, Computer Vision & MLOps (Weeks 19–24)

• Week 19-20: Convolutional Neural Networks (CNNs) & Image Processing
• Week 21-22: Natural Language Processing (NLP), RNNs, Transformers basics
• Week 23-24: Model Deployment (MLOps), Docker, FastApi/Flask & Capstone

Learning Outcomes

• Master mathematical foundations and perform efficient data manipulation in Python.
• Develop, train, and evaluate classical Supervised and Unsupervised ML models.
• Architect and implement Deep Learning solutions for vision and text data using PyTorch/TensorFlow.
• Package and deploy production-ready AI models using MLOps methodologies.

Assessment Weightage

Assessment Type	Weightage
Data Science & ML Assignments	20%
Deep Learning Mini-Projects	25%
Mid-Term Coding & Math Assessment	15%
Final Capstone AI Model Deployment	40%