Computer Science

This course uses interactive visualization to explore and analyze data, structures, and processes. Topics include the fundamental principles, concepts, and techniques of visualization and how visualization can be used to analyze and communicate data in domains such as biology. Students will be expected to design and implement visualizations to experiment with different visual mappings and data types, and will complete a research oriented project.

This course will investigate computational techniques for discovering patterns in and across complex biological and biomedical sources, including genomic and proteomic databases, clinical databases, digital libraries of scientific articles, and ontologies. Techniques covered will be drawn from several areas including sequence mining, statistical natural language processing and text mining, and data mining.

This course will offer a mathematical and practical perspective on artificial neural networks for machine learning. Students will learn about the most prominent network architectures including multilayer feedforward neural networks, convolutional neural networks (CNNs), auto-encoders, recurrent neural networks (RNNs), and generative-adversarial networks (GANs). This course will also teach students optimization and regularization techniques used to train them — such as back-propagation, stochastic gradient descent, dropout, pooling, and batch normalization. Connections to related machine learning techniques and algorithms, such as probabilistic graphical models, will be explored. In addition to understanding the mathematics behind deep learning, students will also engage in hands-on course projects. Students will have the opportunity to train neural networks for a wide range of applications, such as object detection, facial expression recognition, handwriting analysis, and natural language processing.

This course introduces the theory, design, and implementation of text-based and Web-based information retrieval systems. Students learn the key concepts and models relevant to information retrieval and natural language processing on large-scale corpus such as the Web and social systems. Topics include vector space model, crawling, indexing, web search, ranking, recommender systems, embedding and language model.

User modeling is a cross-disciplinary research field that attempts to construct models of human behavior within a specific computer environment. Contrary to traditional artificial intelligence research, the goal is not to imitate human behavior as such, but to make the machine able to understand the expectations, goals, knowledge, information needs, and desires of a user in terms of a specific computing environment. The computer representation of this information about a user is called a user model, and systems that construct and utilize such models are called user modeling systems. A simple example of a user model would be an e-commerce site which makes use of the user’s and similar users’ purchasing and browsing behavior in order to better understand the user’s preferences. In this class, the focus is on obtaining a general understanding of user modeling, and an understanding of how to apply user modeling techniques. Students will read seminal papers in the user modeling literature, as well as complete a course project where students build a system that explicitly models the user.

This course will introduce students to graphical models, such as Bayesian networks, Hidden Markov Models, Kalman filters, particle filters, and structural equation models. Graphical models are applicable in a wide variety of work in computer science for reasoning under uncertainty such as user modeling, speech recognition, computer vision, object tracking, and determining a robot’s location. This course will cover 1) using data to estimate the parameters and structure of a model using techniques such as expectation maximization, 2) understanding techniques for performing efficient inference on new observations such as junction trees and sampling, and 3) learning about evaluation techniques to determine whether a particular model is a good one.

This course introduces students to techniques for performing rigorous empirical research in computer science. Since good empirical work depends on asking good research questions, this course will emphasize creating conceptual frameworks and using them to drive research. In addition to helping students understand what makes a good research question and why, some elementary statistics will be covered. Furthermore, students will use and implement computationally intensive techniques such as randomization, bootstrapping, and permutation tests. The course also covers experiments involving human subjects, and some of the statistical and non-statistical difficulties researchers often encounter while performing such work (e.g., IRB (Institutional Review Board), correlated trials, and small sample sizes). While this course is designed for students in Human Computer Interaction, Interactive Media & Game Development, and Learning Sciences and Technologies, it is appropriate for any student with programming experience who is doing empirical research.

Students will learn how to enable educational technology to adapt to the user and about typical architectures used by existing intelligent tutoring systems for adapting to users. Students will see applications of decision theoretic systems, reinforcement learning, Markov models for action selection, and Artificial Intelligence (AI) planning. Students will read papers that apply AI techniques for the purpose of adapting to users. Students will complete a project that applies these techniques to build an adaptive educational system.

A topic of current interest is covered in detail. Please consult the department for a current listing of selected topics in this area.

This course focuses on human-robot interaction and social robot learning, exploring the leading research, design principles and technical challenges we face in developing robots capable of operating in real-world human environments. The course will cover a range of multidisciplinary topics, including physical embodiment, mixed-initiative interaction, multi-modal interfaces, human-robot teamwork, learning algorithms, aspects of social cognition, and long-term interaction. These topics will be pursued through independent reading, class discussion, and a final project.

This course gives a broad survey of artificial intelligence. The course will cover methods from search, probabilistic reasoning, and learning, among other topics. Selected topics involving the applications of these tools are investigated. Such topics might include natural language understanding, scene understanding, game playing, and planning.

This course examines current issues in the computer implementation of visual perception. Topics include image formation, edge detection, segmentation, shape-from-shading, motion, stereo, texture analysis, pattern classification and object recognition. We will discuss various representations for visual information, including sketches and intrinsic images.

Reinforcement Learning is an area of machine learning concerned with how agents take actions in an environment with a goal of maximizing some notion of “cumulative reward”. The problem, due to its generality, is studied in many disciplines, and applied in many domains, including robotics and industrial automation, marketing, education and training, health and medicine, text, speech, dialog systems, finance, among many others. In this course, we will cover topics including: Markov decision processes, reinforcement learning algorithms, value function approximation, actor-critics, policy gradient methods, representations for reinforcement learning (including deep learning), and inverse reinforcement learning. The course project(s) will require the implementation and application of many of the algorithms discussed in class.

Generative Artificial Intelligence (Gen-AI) is a class of machine learning models that generate new data (text, images, faces, voice, artwork) that is near indistinguishable from the equivalent real data typically generated by humans. These models are trained based on realistic example data sets from the real world. This course covers the underlying fundamentals of generative models. It also introduces the design and modeling of some of the modern generative models: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Diffusion models, ChatGPT, Large Language Models, to name a few. Several applications will be discussed, ranging from image generation for engineering or science applications to the utilization of generated data for data augmentation in AI systems. Ethical concerns related to the danger of these generative technologies concerning issues from misinformation, bias, to data ownership are reviewed.

This course teaches students the computational skills required in the fields of Artificial Intelligence (AI) and Data Science. As data-driven decision-making and AI applications continue to transform industries, proficiency in programming and machine learning tools is important. In this course, you will develop a strong foundation in programming languages commonly used in AI and Data Science (such as Python). This course will cover the development, debugging, deployment, and subsequent monitoring phases of models in end-to-end pipelines core to machine learning systems. You will also familiarize yourself with popular libraries, frameworks and debugging on IDEs, such as PyCharm, PyTorch, scikit-learn, and/or pandas. Possible topics may include practice code development with a copilot as well as deployment of models on a cloud computing environment The student will engage in hands-on projects to practice their programming skills to solve realworld AI and Data Science problems.

Natural Language Processing (NLP) is an interdisciplinary field at the intersection of artificial intelligence, linguistics, and computer science, dedicated to enabling computers to understand, interpret, and generate human language. NLP underpins advancements in human-computer interaction, information retrieval, sentiment analysis, chatbots, and a multitude of other applications. The course may cover a wide range of topics, including language modeling, sequence-to-sequence architectures, sentiment analysis, machine translation, and advanced techniques for natural language understanding and generation, providing a comprehensive foundation for NLP expertise.

Artificial Intelligence (AI) algorithms have a significant impact on people’s lives. In this course, we discuss social responsibility around data privacy, bias in data and decision-making, policies as guardrails, fairness and transparency in the context of applying AI algorithms. Case studies considering societal challenges caused by AI technologies may include AI-based hiring recommendations stemming from societal biases present in training datasets, AI-empowered selfdriving cars behaving in a dangerous manner when encountering atypical road conditions, digital health applications inadvertently revealing private patient information, or large language models like chat-GPT generating incorrect or harmful responses. This course also studies AI-based algorithmic solutions to some of these challenges. These include the design of robust machine learning algorithms with constraints to ensure fairness, privacy, and safety. Strategies for how to apply these methods to design safe and fair AI are introduced. Topics may include min-max optimization with applications to training machine learning models robust to adversarial attacks, stochastic methods for preserving privacy of sensitive data, and multi-agent machine learning models for reducing algorithmic bias and polarization in recommender systems.

To reduce cyber security theory to practice, the capstone project has students apply security concepts to real-world problems. The capstone represents a substantial evaluation of the student’s cyber security experience. Students are encouraged to select projects with practical experience relevant to their career goals and personal development. In the capstone, students will propose a project idea in writing with concrete milestones, receive feedback, and pursue the proposal objectives. Since cyber security is a collaborative discipline, students are encouraged to work in teams.

This course is a degree requirement for the Professional Master’s in Cyber Security (PM-SEC) and may not be taken before completion of 21 credits in the program. Given its particular role, this course may not be used to satisfy degree requirements for a B.S., M.S., or Ph.D. degree in Computer Science or a minor in Computer Science. Students outside the PM-SEC program must get the instructor’s approval before taking this course for credit.

The capstone represents a substantial evaluation of the student’s computer science experience. Students are encouraged to select projects with practical experience relevant to their career goals and personal development. In the capstone, students will propose a project idea in writing with concrete milestones, receive feedback, and pursue the proposal objectives. Students are encouraged to work in teams.

This course is a degree requirement for the Master of Computer Science (MCS) and may not be taken before completion of 21 credits in the program. Given its particular role, this course may not be used to satisfy degree requirements for a BS, MS, or PhD degree in Computer Science or a minor in Computer Science. It may not be taken by students in other degree programs.

This course is focused on fundamentals of network and computer security with an emphasis on how intruders gain access to systems, how they escalate privileges, and what steps can be taken to secure a system against such attacks. Topics include computer networking basics, operating system basics, vulnerability, and attacks (social engineering, distributed denial of service attacks, buffer overflows, race conditions, trojans, and viruses), intrusion penetration, cyber defenses, network hardening, system hardening, and security administration. This course enrolls high school teachers based on their education, teaching, and/or professional experience. They must have earned the equivalent of a four-year U.S. bachelor’s degree to be considered for enrollment. This course is not eligible for credit for the BS/MS programs (either via MS-CS or MS-SEC), MS-CS, MS-SEC, or PhD-CS degrees.

This course covers basic concepts and skills of digital forensics. Topics include the digital forensics profession, basic investigation procedure, legal aspects of forensics, setting up the forensic lab environment, evidence data acquisition, forensic analysis of different computer systems (Linux, Mac, and Windows), and data hiding techniques; projects involving using common digital forensic tools. This course enrolls high school teachers based on their education, teaching, and/or professional experience. They must have earned the equivalent of a four-year U.S. bachelor’s degree to be considered for enrollment. This course is not eligible for credit for the BS/MS programs (either via MS-CS or MS-SEC), MS-CS, MS-SEC, or PhD-CS degrees.

This course is focused on introduction to existing generally accepted guidelines and frameworks (such as HSCCG, CSEC, CAE Knowledge Units, NCWF) in the discipline of cyber security. Methods for teaching cyber security to transform cyber security subject matter, with pedagogical content knowledge, into student learning. Topics include culturally-relevant methods, scaffolding knowledge, differentiation, assessment, and cyber security instructional technologies (ranges, CTFs, competitions, and unplugged activities). This course enrolls high school teachers based on their education, teaching, and/or professional experience. They must have earned the equivalent of a four-year U.S. bachelor’s degree to be considered for enrollment. This course is not eligible for credit for the BS/MS programs (either via MS-CS or MS-SEC), MS-CS, MS-SEC, or PhD-CS degrees.

This 3-credit graduate qualifying project, typically done in teams, provides a capstone experience in applying Artificial Intelligence skills to a real-world problem. It will be carried out in cooperation with an industrial sponsor, and is approved and overseen by a core or collaborative faculty member in the Artificial Intelligence Program. This offering integrates theory and practice of Artificial Intelligence, and includes the utilization of tools and techniques acquired in the Artificial Intelligence Program to a real-world problem. In addition to a written report, this project must be presented in a formal presentation to faculty of the AI program and sponsors. Professional development skills, such as communication, teamwork, leadership, and collaboration, will be practiced. This course is a degree requirement for the Master of Science in Artificial Intelligence (MS-AI) and may not be taken before completion of 21 credits in the program. Students outside the MS-AI program must get the instructor’s approval before.

This course focuses on providing students practical hands-on experiences on digital forensics, cyber-crime scene analysis and electronic discovery. Topics include technical methodologies and formal procedures for conducting forensic investigations; data acquisition, data recovery, file systems and storage analysis, file carving, data hiding and steganography, anti-forensics, network, and mobile forensics; projects involving using, understanding, and designing digital forensics tools. This course enrolls high school teachers based on their education, teaching, and/or professional experience. They must have earned the equivalent of a four-year U.S. bachelor’s degree to be considered for enrollment. This course is not eligible for credit for the BS/MS programs (either via MS-CS or MS-SEC), MS-CS, MS-SEC, or PhD-CS degrees.

This course provides deeper insight into areas of cryptography which are of great practical and theoretical importance. The three areas treated are detailed analysis and the implementation of cryptoalgorithms, advanced protocols, and modern attacks against cryptographic schemes. The first part of the lecture focuses on public key algorithms, in particular ElGamal, elliptic curves and Diffie-Hellman key exchange. The underlying theory of Galois fields will be introduced. Implementation of performance security aspects of the algorithms will be looked at. The second part of the course deals with advanced protocols. New schemes for authentication, identification and zero-knowledge proof will be introduced. Some complex protocols for real-world application— such as key distribution in networks and for smart cards—will be introduced and analyzed. The third part will look into state-of-the-art cryptoanalysis (i.e., ways to break cryptosystems). Brute force attacks based on special purpose machines, the baby-step giant-step and the Pohlig-Hellman algorithms will be discussed.

This course is focused on significant programming projects and provides an overview of the principles of computer networks and a general-purpose operating system. The course provides the student with an understanding of the basic components of an operating system, including processes, synchronization and memory management. The course exposes students to the Internet protocol suite networking layers while providing an introduction into topics such as wireless networking and Internet traffic considerations. The objective is to focus on an understanding of fundamental concepts of operating systems and computer network architecture from a design and performance perspective.

Students will be expected to design and implement a variety of programming projects to gain an appreciation of the design of operating systems and network technologies. This course may not be used to satisfy degree requirements for a B.S., M.S., or Ph.D. degree in Computer Science or a minor in Computer Science. It may satisfy the requirements for other degree programs at the discretion of the program review committee for the particular degree.

This course will offer a mathematical and practical perspective on artificial neural networks for machine learning. Students will learn about the most prominent network architectures including multilayer feedforward neural networks, convolutional neural networks (CNNs), auto-encoders, recurrent neural networks (RNNs), and generative-adversarial networks (GANs). This course will also teach students optimization and regularization techniques used to train them — such as back- propagation, stochastic gradient descent, dropout, pooling, and batch normalization. Connections to related machine learning techniques and algorithms, such as probabilistic graphical models, will be explored. In addition to understanding the mathematics behind deep learning, students will also engage in hands-on course projects. Students will have the opportunity to train neural networks for a wide range of applications, such as object detection, facial expression recognition, handwriting analysis, and natural language processing.

This course introduces the theory, design, and implementation of text-based and Web-based information retrieval systems. Students learn the key concepts and models relevant to information retrieval and natural language processing on large-scale corpus such as the Web and social systems. Topics include vector space model, crawling, indexing, web search, ranking, recommender systems, embedding and language model.

Deep Learning, a core of modern Artificial Intelligence, is rapidly expanding to resourceconstrained devices, including smartphones, wearables, and intelligent embedded systems for improving response time, privacy, and reliability. This course focuses on bringing these powerful deep-learning applications from central data centers and large GPUs to distributed ubiquitous systems. On-Device Deep Learning is an interdisciplinary topic at the intersection of artificial intelligence and ubiquitous systems, dedicated to enabling computing on edge devices. This course includes a wide range of topics related to deep learning in resource constrained settings including pruning and sparsity, quantization, neural architecture search, knowledge distillation, on-device training and transfer learning, distributed training, gradient compression, federated learning, efficient data movement and accelerator design, dynamic network inference, and advanced compression and approximation techniques for enabling on-device deep neural network inference and training. This course provides a comprehensive foundation for cutting-edge “tinyML” expertise

To reduce cyber security theory to practice, the capstone project has students apply security concepts to real-world problems. The capstone represents a substantial evaluation of the student’s cyber security experience. Students are encouraged to select projects with practical experience relevant to their career goals and personal development. In the capstone, students will propose a project idea in writing with concrete milestones, receive feedback, and pursue the proposal objectives. Since cyber security is a collaborative discipline, students are encouraged to work in teams.

This course is a degree requirement for the Professional Master’s in Cyber Security (PM-SEC) and may not be taken before completion of 21 credits in the program. Given its particular role, this course may not be used to satisfy degree requirements for a B.S., M.S., or Ph.D. degree in Computer Science or a minor in Computer Science. Students outside the PM-SEC program must get the instructor’s approval before taking this course for credit.

This course provides deeper insight into areas of cryptography which are of great practical and theoretical importance. The three areas treated are detailed analysis and the implementation of cryptoalgorithms, advanced protocols, and modern attacks against cryptographic schemes. The first part of the lecture focuses on public key algorithms, in particular ElGamal, elliptic curves and Diffie-Hellman key exchange. The underlying theory of Galois fields will be introduced. Implementation of performance security aspects of the algorithms will be looked at. The second part of the course deals with advanced protocols. New schemes for authentication, identification and zero-knowledge proof will be introduced. Some complex protocols for real-world application— such as key distribution in networks and for smart cards—will be introduced and analyzed. The third part will look into state-of-the-art cryptoanalysis (i.e., ways to break cryptosystems). Brute force attacks based on special purpose machines, the baby-step giant-step and the Pohlig-Hellman algorithms will be discussed.

This course examines current issues in the computer implementation of visual perception. Topics include image formation, edge detection, segmentation, shape-from-shading, motion, stereo, texture analysis, pattern classification and object recognition. We will discuss various representations for visual information, including sketches and intrinsic images.

User modeling is a cross-disciplinary research field that attempts to construct models of human behavior within a specific computer environment. Contrary to traditional artificial intelligence research, the goal is not to imitate human behavior as such, but to make the machine able to understand the expectations, goals, knowledge, information needs, and desires of a user in terms of a specific computing environment. The computer representation of this information about a user is called a user model, and systems that construct and utilize such models are called user modeling systems. A simple example of a user model would be an e-commerce site which makes use of the user’s and similar users’ purchasing and browsing behavior in order to better understand the user’s preferences. In this class, the focus is on obtaining a general understanding of user modeling, and an understanding of how to apply user modeling techniques. Students will read seminal papers in the user modeling literature, as well as complete a course project where students build a system that explicitly models the user.

This course will introduce students to graphical models, such as Bayesian networks, Hidden Markov Models, Kalman filters, particle filters, and structural equation models. Graphical models are applicable in a wide variety of work in computer science for reasoning under uncertainty such as user modeling, speech recognition, computer vision, object tracking, and determining a robot’s location. This course will cover 1) using data to estimate the parameters and structure of a model using techniques such as expectation maximization, 2) understanding techniques for performing efficient inference on new observations such as junction trees and sampling, and 3) learning about evaluation techniques to determine whether a particular model is a good one.

This course introduces students to techniques for performing rigorous empirical research in computer science. Since good empirical work depends on asking good research questions, this course will emphasize creating conceptual frameworks and using them to drive research. In addition to helping students understand what makes a good research question and why, some elementary statistics will be covered. Furthermore, students will use and implement computationally intensive techniques such as randomization, bootstrapping, and permutation tests. The course also covers experiments involving human subjects, and some of the statistical and non-statistical difficulties researchers often encounter while performing such work (e.g., IRB (Institutional Review Board), correlated trials, and small sample sizes). While this course is designed for students in Human Computer Interaction, Interactive Media & Game Development, and Learning Sciences and Technologies, it is appropriate for any student with programming experience who is doing empirical research.

Students will learn how to enable educational technology to adapt to the user and about typical architectures used by existing intelligent tutoring systems for adapting to users. Students will see applications of decision theoretic systems, reinforcement learning, Markov models for action selection, and Artificial Intelligence (AI) planning. Students will read papers that apply AI techniques for the purpose of adapting to users. Students will complete a project that applies these techniques to build an adaptive educational system.