Coursework at Carnegie Mellon University

This course explores optimization algorithms essential for machine learning, focusing on convex optimization techniques for solving objective functions, both with and without constraints. Topics include first-order methods (gradient descent, stochastic gradient descent), duality, linear programming, second-order methods, and advanced techniques such as adaptive gradients and distributed optimization, all framed within practical machine learning applications.

This course provided in-depth knowledge of integer programming with non-linear objective functions and the application of quantum computing to combinatorial optimization. Gained practical experience using quantum computing resources like DWave Quantum Annealers and worked on collaborative projects in the field.

This advanced course addresses the critical challenge of ensuring safety in AI-driven autonomy, covering topics like adversarial defense, generative models, and safe reinforcement learning. It equips students with research skills to explore cutting-edge trustworthy AI methods and their applications in real-world systems like self-driving cars and healthcare devices. Designed for research-oriented students in machine learning, robotics, and human-machine interaction, the course fosters team-based research capabilities essential for developing secure and reliable autonomous systems

This course provides a foundation in decision-making methods, focusing on solving systems engineering problems using stochastic programming and robust optimization. It covers simulation, optimization, and synthesis techniques for decision making and scheduling problems.

This course covers foundational machine learning and AI techniques essential for engineers, including Bayesian learning, neural networks, SVMs, clustering, regression, and optimization. Emphasis is on theoretical foundations and mathematical modeling to equip students with robust problem-solving skills for data-intensive applications.

This course focuses on developing a solid foundation in AI infrastructure, teaching students to design, implement, and manage AI systems at scale using modern frameworks and cloud environments. Offers hands on experience with industry-standard tools like Apache Spark, TensorFlow, Apache Kafka, and PostgreSQL.