Coursework

This course delves into the crucial intersection of 3D vision and deep learning, focusing on how autonomous agents perceive and act in a 3D world. Students develop a solid foundation in explicit and implicit 3D representations such as point clouds, NeRFs, and meshes, along with techniques like differentiable rendering and single-view 3D prediction using CNNs. Key topics include multi-view 3D optimization, view synthesis, neural rendering, and inference with point clouds and meshes. Through assignments and projects, learners gain hands-on experience applying these advanced methods to challenges in robotics, computer vision, and AR/VR, equipping them to innovate in research and industry

This course provides a thorough introduction to deep learning, covering foundational concepts of deep neural networks and their applications across engineering domains. Key topics include neural networks, convolutional neural networks (CNNs), backpropagation, and automatic differentiation. Students also learn advanced techniques such as recurrent neural networks (RNNs), generative adversarial networks (GANs), attention models, transformers, and diffusion models. Practical implementation skills are developed using PyTorch, enabling students to design, train, and deploy deep learning models for diverse AI tasks relevant to engineering challenges.

This course focuses on the innovative application of Artificial Intelligence to design, build, and scale business models throughout the business lifecycle. Graduate students explore how AI enhances ideation, development, and scaling of enterprises, with special attention to integrating AI into legacy organizations. Key topics include leveraging AI for business modeling, defining AI product value propositions, building AI teams, and managing AI adoption challenges. Through team projects, case studies, and presentations, students gain practical experience designing AI-based startups and learn to bridge advanced AI techniques with business foundations for real-world impact.

This course explores the theory and algorithms behind simultaneous localization and mapping, a core challenge for mobile robots across domains such as autonomous driving, aerial drones, underwater vehicles, and AR/VR systems. Students examine probabilistic inference methods, including Bayes, particle, and Kalman filters, as well as nonlinear least-squares optimization and inference in graphical models. Emphasis is placed on robust, real-time solutions that address sensor uncertainty and scalability. Through hands-on assignments, the course bridges linear algebra, probability theory, and state-of-the-art SLAM systems, fostering skills applicable far beyond robotics.

This course provides a hands-on introduction to the analysis and design of model-based controllers for multi-input, multi-output linear systems. Students explore state-space modeling, linearization, and the structural properties of dynamic systems, including stability, controllability, and observability. Core topics include pole placement, optimal control (LQR, MPC), and stochastic estimation with the Kalman filter. Emphasis is placed on both analytical and numerical solution methods, supported by Matlab/Simulink simulations. By connecting linear algebra principles with real-world applications in control and robotics, the course equips students to design and implement robust state-space controllers in practical scenarios.

This course offers a comprehensive introduction to the core concepts, algorithms, and mathematical foundations of machine learning and artificial intelligence. Students explore supervised and unsupervised learning, Bayesian methods, neural networks, support vector machines, clustering, regression, dimensionality reduction, and optimization, alongside evolutionary computation and search techniques. Emphasis is placed on both theory and practical implementation using Python for data processing, visualization, and algorithm development. Through hands-on assignments, the course bridges probability, statistics, linear algebra, and programming skills, equipping students to design and implement intelligent, data-driven solutions to complex engineering problems.