Machine Learning

• Python Fundamentals: Syntax, Data Types, Control Flow

• Functions, Lambda, Decorators & Generators

• OOP Concepts, Modules & Packages

• Data Structures & Algorithmic Problem Solving

• Exception Handling & File Handling

• APIs & Web Data Integration (REST, JSON, Requests)

• Libraries for AI: NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn

• NEW: PyTorch Lightning & TensorFlow 2.x Overview

• Bonus: Best Practices for Clean Code & Performance Optimization

• Cloud Computing Fundamentals (AWS, GCP, Azure)

• Cloud-based ML Services: AWS SageMaker, GCP Vertex AI, Azure ML Studio

• Version Control with Git & GitHub

• OS & Shell Scripting for Data Workflows

• CI/CD for ML Pipelines – GitHub Actions, Jenkins, Azure DevOps

• Containerization using Docker & Kubernetes

• NEW: Deploying Models with Streamlit & Gradio on Cloud

• Descriptive & Inferential Statistics

• Probability Theory & Distributions

• Linear Algebra for ML: Vectors, Matrices, Eigenvalues

• Calculus for Optimization

• Gradient Descent, Loss Functions & Regularization

• Numerical Methods & Convergence

• NEW: Hands-on with Python (NumPy/SciPy) for Math Concepts

• Relational & Non-Relational Databases

• SQL Basics: DDL, DML, DQL, TCL

• Aggregations, Grouping, and Complex Joins

• Subqueries, Nested Queries & Window Functions

• Query Optimization & Performance Tuning

• NEW: Data Pipelines using Airflow & DBT

• NEW: Introduction to NoSQL (MongoDB) for Unstructured Data

• EDA Workflow & Hypothesis Testing

• Data Cleaning, Transformation, and Feature Engineering

• Statistical Summary & Correlation Analysis

• Visualization with Matplotlib, Seaborn, and Plotly

• Power BI & Tableau for Business Visualization

• NEW: Automated EDA Tools (Sweetviz, Pandas-Profiling)

• Supervised Learning: Regression, Classification

• Unsupervised Learning: Clustering, PCA, Dimensionality Reduction

• Model Evaluation Metrics (Accuracy, Precision, Recall, ROC, AUC)

• Bias-Variance Trade-off & Cross-Validation

• NEW: Explainable AI (SHAP, LIME)

• Model Deployment using Flask & FastAPI

• NEW: Feature Store & Data Versioning

• Ensemble Methods: Bagging, Boosting, Stacking

• Boost, LightGBM, CatBoost

• Hyperparameter Tuning (Grid, Random, Bayesian Search)

• Feature Selection & Dimensionality Reduction

• NEW: Auto ML Tools (H2O.ai, Auto-Sklearn, PyCaret)

• NEW: Model Monitoring & Drift Detection

• Neural Network Fundamentals: Perceptron, MLP

• Activation Functions, Optimizers & Loss Functions

• CNNs for Image Recognition (VGG, ResNet, EfficientNet)

• RNN, LSTM, GRU for Sequential Data

• Transfer Learning & Fine-Tuning

• NEW: Vision Transformers (ViT), CLIP Models

• NEW: Neural Network Deployment using ONNX & TorchServe

• NLP Fundamentals & Text Preprocessing

• Word Embeddings: Word2Vec, GloVe, TF-IDF

• Sequence Models (RNN, LSTM, GRU)

• Transformers Architecture & BERT Models

• Named Entity Recognition (NER) & Sentiment Analysis

• NEW: LLM Fine-tuning (BERT, GPT) using Hugging Face

• NEW: LangChain, Vector Databases (FAISS, Chroma DB)

• Introduction to Generative AI & LLMs

• GPT, Claude, Gemini – Ecosystem Overview

• GANs, VAEs, Diffusion Models

• Text-to-Image Models (Stable Diffusion, DALL·E)

• Prompt Engineering Techniques & Templates

• NEW: Fine-Tuning & Retrieval-Augmented Generation (RAG)

• NEW: Prompt Patching, Chain-of-Thought, and Context Injection

• Ethical AI & Responsible Prompting

• Introduction to MLOps

• End-to-End ML Lifecycle

• CI/CD for ML Pipelines

• Model Tracking with MLflow, DVC

• Model Versioning, Deployment & Monitoring

• Containerization with Docker & Kubernetes

• NEW: Kubeflow & Vertex AI Pipelines

• NEW: Cloud MLOps (AWS SageMaker Pipelines, Azure ML)

• Capstone: Full MLOps Project from Training to Deployment

• Predictive Analytics (Finance, Retail, Healthcare)

• Computer Vision Project (Face Recognition, Defect Detection)

• NLP Project (Chatbot, Sentiment Analyzer)

• Generative AI Project (LLM-based Assistant or Content Generator)

• MLOps Pipeline Deployment (End-to-End)