Courses

This course covers basic as well as advanced concepts to gain a detailed understanding of Natural Language Processing tasks such as language modeling, text to speech generation, natural language understanding, and natural language generation. Students can learn the necessary skills to design a range of applications, including sentiment analysis, translating between languages, and answering questions. The practical implementation of these applications with deep neural networks is also discussed.

This course will teach the foundations of AI and give students a practical understanding of the field. This course gives an overview of the core concepts of AI, including the intelligent agents, knowledge and reasoning, reinforcement learning, planning and acting, belief networks, computational learning, Markov decision process, and more.

This course focuses on the design of computer-based, machine vision systems using appropriate algorithms and best practices. Students will learn image representation and structuring; feature extraction and segmentation; and information extraction, filtering, and analysis.

This course will cover the foundations on neural networks and deep learning networks. It covers the core concepts of deep neural networks, including the convolutional neural networks for image recognition, recurrent neural networks for sequence generation, and generative adversarial networks for image generation.

This course will explore the development of analytics systems and the application of best practices and established software design principles using the Python programming language and its several toolkits.

Descriptive statistics, hypothesis testing, power, estimation, confidence intervals, regression, one- and two-way ANOVA, chi-square tests, diagnostics.

This course will cover the main theory and approaches of reinforcement learning, along with deep learning and common software libraries and packages.

Examines tools and techniques required for data collection and computational procedures to automatically identify and eliminate errors in large datasets

The objective of this course is to provide a foundation in the principles of network and predictive analytics along with hands-on experience with statistical analysis software for studying the interrelatedness of cyber-social and cyber-technical aspects of our society as a whole.

This course provides a foundation in the principles, concepts, techniques, and tools for visualizing large data sets.

The theory and application of several quantitative decision-making tools will be studied. The usefulness of these tools will be illustrated using projects and case studies throughout the course. Emphasis will be placed on the application of the tools and techniques and the results they generate.

Survey course on the key topics in predictive analytics. Students will learn methods associated with data analytics techniques and apply them to real examples using the R statistical system.

Practical benefits of data mining will be presented; data warehousing, data cubes, and underlying algorithms used by data mining software.

The choice of project topic and exact form will be mutually determined by you and your instructor. A written paper based on the applied project is required and must contain project description, analysis, and interpretation of findings.