The courses will introduce Artificial Intelligence and Machine Learning topics with practical examples of data, tools, and algorithms. In addition to C, C++, and Matlab, a scripting language (i.e. Python) will be used and taught throughout the course. The course will explore basic artificial intelligence techniques and their applications to engineering problems. Students will be introduced to the following AI foundations: probability and linear algebra, state spaces, algorithms, data processing, feature extraction, feature reduction, classification, and decision making. Some of the techniques and tools to be covered in this course are inference, regression, linear discriminant analysis, decision trees, neural networks, deep learning platforms and architectures, and reinforcement learning. Students are expected to have any of the following programming skills: C/C++, Matlab, Java, or any other high level programming language.

One semester of paid work experience in electrical engineering.

Cybernetics refers to the science of communication and control theory that is concerned especially with the comparative study of automatic control systems (as in the nervous system and brain and mechanical- electrical communications systems). This course will present material related to the study of cybernetics as well as the aspects of robotics and controls associated with applications of a biological nature. Topics will also include the study of various paradigms and computational methods that can be utilized to achieve the successful integration of robotic mechanisms in a biological setting. Successful participation in the course will entail completion of at least one project involving incorporation of these techniques in a biomedical application.

The course will start with the history of artificial intelligence and its development over the years. There have been many attempts to define and generate artificial intelligence. As a result of these attempts, many artificial intelligence techniques have been developed and applied to solve real life problems. This course will explore variety of artificial intelligence techniques, and their applications and limitations. Some of the AI techniques to be covered in this course are intelligent agents, problem-solving, knowledge and reasoning, uncertainty, decision making, learning (Neural networks and Bayesian networks), reinforcement learning, swarm intelligence, Genetic algorithms, particle swarm optimization, applications in robotics, controls, and communications. Students are expected to have any of the following programming skills listed above. Students will write an IEEE conference paper.

Cybernetics refers to the science of communication and control theory that is concerned especially with the comparative study of automatic control systems (as in the nervous system and brain and mechanical-electrical communications systems). This course will present material related to the study of cybernetics as well as the aspects of robotics and controls associated with applications of a biological nature. Topics will also include the study of various paradigms and computational methods that can be utilized to achieve the successful integration of robotic mechanisms in a biological setting. Successful participation in the course will entail completion of at least one project involving incorporation of these techniques in a biomedical application. Students are required to write an IEEE conference paper on their projects.

The course will start with the history of artificial intelligence (AI) and its development over the years. There have been many attempts to define and generate artificial intelligence. As a result of these attempts, many AI techniques have been developed and applied to solve real life problems. This course will explore a variety of AI techniques and their applications and limitations. Some of the AI topics to be covered in this course are intelligent agents, problem-solving, knowledge and reasoning, uncertainty, decision making, machine learning, reinforcement learning, and real-world applications of AI. Students are expected to have solid programming skills, understanding of probability and linear algebra, and statistics. Students will write a conference-style paper based on a research project.

This course is an introduction to machine learning theories and algorithms. Topics include an overview of data collection, sampling and visualization techniques, supervised and unsupervised learning and graphical models. Specific techniques that may be covered include classification (e.g., support vector machines, tree-based models, neural networks), regression, model selection and some deep learning techniques. Programming assignments and oral/written summaries of research papers are required.