📚 Course Catalog

Data lifecycle, Python setup, exploratory analysis, and the data science toolkit.

Derivatives, integrals, multivariate calculus, and gradient descent foundations.

Vectors, matrices, eigenvalues, and their applications in machine learning.

Python fundamentals, data structures, OOP, and scripting for data workflows.

Descriptive stats, probability, distributions, hypothesis testing, and regression.

Pandas, data cleaning, joining, and visual storytelling with Matplotlib, Seaborn, Plotly.

Supervised/unsupervised learning, decision trees, SVMs, model evaluation.

Relational databases, SQL mastery, query optimization, NoSQL introduction.

EDA workflow, statistical testing, pattern discovery, and business storytelling.

Probability spaces, random variables, Bayesian statistics, and stochastic processes.

ETL, Apache Airflow, data lake architectures, and pipeline monitoring.

Spark, Hadoop, distributed processing, and streaming with Kafka.

Neural networks from scratch, CNNs, RNNs, Transformers, and training techniques.

Text processing, word embeddings, transformers, and fine-tuning LLMs.

Image classification, object detection, segmentation, and OpenCV.

ARIMA, LSTM for sequences, anomaly detection, and forecasting.

AWS/GCP/Azure for data science, cloud storage, compute, and deployment.

Bias, fairness, privacy, accountability, and responsible data practices.

First half of semester-long industry data science project with real data.

Final delivery, presentation, and written thesis of the capstone project.

Bayesian methods, MCMC, regularization theory, and model selection at depth.

Distributed compute, data lake design, streaming systems, and cloud-native architectures.

Vision Transformers, Diffusion Models, Graph Neural Networks, and advanced optimization.

CI/CD for ML, feature stores, model registries, A/B testing, and drift detection.

LLMs, diffusion models, multimodal AI, and generative applications in industry.

Real-world project with an industry partner. Deliverable is a working data product.

Original research contribution. Supervised by a faculty member over two semesters.

Thesis defense, oral examination, and preparation of publication-ready manuscript.

AI engineering landscape, model lifecycle, and intro to the engineering toolchain.

Arrays, trees, graphs, sorting, searching, and complexity analysis.

SDLC, design patterns, version control, testing, and agile methodology.

Engineering perspective on ML: feature engineering, model selection, and training pipelines.

AWS/GCP/Azure, Docker, Kubernetes, CI/CD pipelines, and infrastructure as code.

REST APIs, gRPC, microservice architecture, and service mesh patterns.

Model versioning, CI/CD for ML, A/B testing, drift detection, and monitoring.

Distributed training, parameter servers, data parallelism, and fault tolerance.

Low-latency serving, streaming inference, batching, and SLA management.

Observability, alerting, SLOs, incident response, and root cause analysis for AI systems.

System design for AI: scalability, trade-offs, case studies, and architecture patterns.

Industry-partner AI engineering project. Team builds, deploys, and monitors a production AI system.

History, philosophy, core AI paradigms — from symbolic logic to modern deep learning.

Supervised learning, overfitting, regularization, and the ML pipeline from scratch.

Logic, sets, graphs, combinatorics, and formal reasoning for AI.

BFS, DFS, A*, minimax, and constraint satisfaction problems.

Perceptrons, backpropagation, activation functions, and training dynamics.

CNNs, RNNs, Transformers, training techniques, and PyTorch mastery.

MDPs, Q-learning, policy gradients, actor-critic, and deep RL.

VAEs, GANs, Diffusion Models, and Flow-based models — theory and implementation.

Self-attention, BERT, GPT, fine-tuning, RLHF, and prompt engineering.

Major AI research project with real experimental contribution and written report.