Introduction to AI, ML, and their differences

Overview of use cases: vision, language, recommendation

Setting up Python environment (Anaconda, Jupyter)

Installing key libraries: NumPy, pandas, scikit-learn

Understanding datasets: tabular, images, text

Working with scikit-learn: building simple models

Introduction to TensorFlow / Keras basics

Using Google Colab or local GPU setup

Loading and transforming data pipelines

Understanding APIs and model saving

Handling missing values, outliers

Encoding categorical features, one-hot, label encoding

Feature scaling: normalization, standardization

Feature creation, selection, dimensionality reduction

Splitting data: train, validation, test

Choosing models: linear regression, decision trees, SVM, kNN

Loss functions and optimization techniques

Cross validation, grid search, hyperparameter tuning

Overfitting vs underfitting, bias-variance tradeoff

Evaluation metrics: accuracy, precision, recall, F1, ROC/AUC

Neural network architecture basics: layers, activations

Building simple feedforward networks

Introduction to CNNs (for image tasks) and RNNs (for text)

Transfer learning with pretrained models

Regularization: dropout, batch normalization

Sentiment analysis on text data

Image classification (cats vs dogs or similar)

Recommendation system basics

Time series forecasting

Building a chatbot or simple NLP pipeline

Converting models to serveable format (e.g. ONNX, TensorFlow SavedModel)

Deploying model via simple web app (Flask / FastAPI)

Setting up inference API endpoints

Monitoring model performance, logging predictions

Handling real-time updates and retraining