• History & evolution of AI
• AI vs Machine Learning vs Deep Learning
• Real-world AI applications and industry examples
• Course overview, tools, and environment setup (Python, Jupyter)

• Data acquisition: CSV, APIs, databases, scraping basics
• Data cleaning: missing values, outliers, duplicates
• Feature engineering and encoding categorical variables
• Scaling, normalization, and feature selection
• Exploratory Data Analysis (visualization + insights)

• Decision Trees and Ensemble Methods (Random Forest, XGBoost, LightGBM)
• Gradient boosting concepts and tuning
• Hyperparameter tuning (GridSearch, RandomSearch)
• Feature importance and model interpretation

• Image preprocessing and augmentation
• CNN layers, pooling, architecture patterns (VGG, ResNet)
• Transfer learning and fine-tuning pretrained models
• Building image classifiers and evaluation metrics

• Introduction to LLMs and generative models
• Prompt engineering best practices
• Using OpenAI / Hugging Face APIs for text generation
• Building a simple conversational agent and evaluation

• Serving models with FastAPI / Flask / TorchServe
• Containerization (Docker) and basic Kubernetes concepts
• CI/CD for ML pipelines, model versioning, and monitoring (Prometheus, Grafana)
• Logging, metrics, and drift detection

• Python fundamentals: data types, control flow, functions
• Working with Jupyter Notebooks
• NumPy for numerical computing
• Pandas for data manipulation
• Visualization basics with Matplotlib / Seaborn

• Supervised vs Unsupervised learning concepts
• Regression algorithms (Linear, Ridge, Lasso)
• Classification algorithms (Logistic Regression, KNN)
• Model evaluation: confusion matrix, precision, recall, F1, ROC-AUC
• Cross-validation and train/test split

• Neural network basics: perceptron, MLP architecture
• Activation functions, loss functions, optimizers
• Introduction to TensorFlow & Keras (or PyTorch)
• Training loop, callbacks, early stopping, model saving

• Text preprocessing: tokenization, stemming, lemmatization
• Vectorization: Bag-of-Words, TF-IDF, word embeddings (Word2Vec/GloVe)
• Sequence models: RNNs, LSTM basics
• Transformer models overview (BERT/GPT) and practical examples

• Automating workflows with AI (n8n / Power Automate overview)
• Integrating LLMs into business processes (RAG, tool calling)
• Building simple autonomous agents for tasks (email draft, scheduling)
• Monitoring and safety for automated agents

• End-to-end capstone: select project (CV/NLP/LLM) and delivery
• Project documentation, reproducibility, and code walk-through
• Resume & LinkedIn optimization for AI roles
• Mock interviews (technical, system design, ML case studies) and career guidance