Search Results

Machine Learning is a computational approach for construction of algorithms that can learn from and make predictions on data. The focus of the course is to deliver a practical approach that can help appropriate utilization of machine learning methods for data exploration and prediction tasks in biomedical applications. Applications will be drawn from bioinformatics, neuro-engineering, and biomedical image analysis, with special emphasis given to feature extraction and representation strategies specific to the data types prevalent in these domains. The machine learning concepts and methods will include parameter density estimation, dimension reduction, supervised and unsupervised learning, neural networks, and support vector machines.

College/Department: School of Biomedical Engineering, Science Health Systems
Repeat Status: Not repeatable for credit
Prerequisites: BMES 546 [Min Grade: B] or BMES 550 [Min Grade: B]

This course is a survey of statistical learning methods and will cover major techniques and concepts for both supervised and unsupervised learning. Topics include penalized regression and classification, support vector machines, kernel methods, model selection, clustering, boosting, CART and random forests, and ensemble learning. Students will learn how and when to apply statistical learning techniques, their comparative strengths and weaknesses, how to critically evaluate the performance of learning algorithms, and principles for appropriate application to health science problems. The statistical programming language R will be used throughout.

College/Department: Dornsife School of Public Health
Repeat Status: Not repeatable for credit
Prerequisites: BST 701 [Min Grade: C]

This introductory course provides a broad exploration of artificial intelligence (AI) and machine learning (ML), focusing on fundamental concepts, real-world applications, and emerging trends. Students will learn about the history of AI, problem-solving strategies, search algorithms, adversarial agents, classification and clustering techniques, neural networks and deep learning, reinforcement learning, generative AI, and large language models. Ethical considerations, societal impacts, and the future of AI will also be discussed. No prior programming experience is required.

College/Department: LeBow College of Business
Repeat Status: Not repeatable for credit

This introductory course provides a broad exploration of artificial intelligence (AI) and machine learning (ML), focusing on fundamental concepts, real-world applications, and emerging trends. Students will learn about the history of AI, problem-solving strategies, search algorithms, adversarial agents, classification and clustering techniques, neural networks and deep learning, reinforcement learning, generative AI, large language models, and AI in games. Ethical considerations, societal impacts, and the future of AI will also be discussed. No prior programming experience is required.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit

This course covers the fundamentals of modern statistical machine learning. Lectures will cover the theoretical foundation and algorithmic details of representative topics including probabilities and decision theory, regression, classification, graphical models, mixture models, clustering, expectation maximization, hidden Markov models, and weak learning.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: CS 260 [Min Grade: C] and (MATH 201 [Min Grade: C] or ENGR 231 [Min Grade: D]) and (MATH 221 [Min Grade: C] or MATH 222 [Min Grade: C]) and (MATH 311 [Min Grade: C] or MATH 410 [Min Grade: C] or ECE 361 [Min Grade: D])

This course introduces students to the understanding about the robustness and vulnerability of current state-of-the-art machine learning systems. Lectures will cover the theoretical foundation and algorithmic details of different types of adversarial attack and defense methods accordingly on multiple machine learning tasks including image classification, object detection, natural language processing, etc. Students will understand the intriguing property of deep learning systems and know the significance of robust and trustworthy machine learning.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: CS 380 [Min Grade: C] or CS 383 [Min Grade: C]

With the rapid deployment of machine learning models in domains such as lending, sentencing, and hiring, it is essential to understand the ethical aspects and negative consequences of such models. In this course, we focus on three of these aspects: fairness, explainability, and recourse.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: CS 504 [Min Grade: C]

This course explores artificial intelligence (AI) and machine learning (ML) in practice as an open-ended team activity. Initiates an in-depth multi-term capstone study applying computing and informatics knowledge in an AI/ML project. Teams work to develop a significant product with advisors from industry and/or academia. Explores AI/ML-related issues and challenges involved in the application domain of the team’s choice. Applies a development process structure for project planning, specification, design, implementation, evaluation, and documentation.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: (CS 510 [Min Grade: C] and CS 613 [Min Grade: C] and CS 615 [Min Grade: C]) or (CS 614 [Min Grade: C] and INFO 629 [Min Grade: C])

This course explores artificial intelligence (AI) and machine learning (ML) in practice as an open-ended team activity. Completes an in-depth multi-term capstone study applying computing and informatics knowledge in an AI/ML project. Teams work to develop a significant product with advisors from industry and/or academia. Explores AI/ML-related issues and challenges involved in the application domain of the team’s choice. Applies a development process structure for project planning, specification, design, implementation, evaluation, and documentation.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: CS 591 [Min Grade: C]

This course studies modern statistical machine learning with emphasis on Bayesian modeling and inference. Covered topics include fundamentals of probabilities and decision theory, regression, classification, graphical models, mixture models, clustering, expectation maximization, hidden Markov models, Kalman filtering, and linear dynamical systems.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: CS 504 [Min Grade: C]

Machine learning (ML) learns concepts from data to perform complex tasks to solve a variety of challenging problems. With the growth and abundance of data sources and types, ML methods become more sophisticated and give rise to applications in new areas accomplishing tasks perceived as impractical or not feasible before. This course educates students to recognize the relevant factors in applying ML methods and architectures to different application problems in various application domains. The focus on specific application domains, tasks, and areas may vary depending on students’ interest but will cover the essential problem areas of artificial intelligence such as vision, natural language, recommender systems, and applications in the biomedical field.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: INFO 629 [Min Grade: C] or CS 613 [Min Grade: C] or DSCI 631 [Min Grade: C]

Introduces relevant topics in the life cycle of machine learning: extracting and engineering features, tuning parameters, comparing algorithms, interpreting results, and analyzing errors. Students will be exposed to various representative algorithms in the concept level and learn their trade-offs. Students will gain hands-on experiences with assignments and a term project. Students will be prepared to attack new problems using various machine learning methods and be able to compare the performance of different algorithms for the term project.

College/Department: College of Computing and Informatics
Repeat Status: Not repeatable for credit
Prerequisites: DSCI 521 [Min Grade: C] (Can be taken Concurrently)

This course emphasizes how to gather data then train, test, and deploy practical machine learning systems using modern software libraries, with an emphasis on scikit-learn, Keras on TensorFlow, and TensorFlow Agents. After garnering working familiarity with learning architectures including linear regression, support vector machines, decision trees, and deep neural networks, students will shift to practicing techniques that leverage state of the art published models via transfer learning. This is a hands-on project-focused course integrating coding activities into lectures. To provide the broadest applicability, datasets will range from rich text, to financial time series, to sound, images, and video, as well as data garnered through game play.

College/Department: College of Engineering
Repeat Status: Not repeatable for credit
Prerequisites: ECE 105 [Min Grade: D] or CS 172 [Min Grade: D]

This course introduces students to topics in modern machine learning, along with applications of machine learning to problems in engineering. Introductory topics will include an overview of classification, overfitting, cross-validation, and dimensionality reduction. Supervised classification approaches will be covered including linear classifiers, generative and discriminative models, non-probabilistic classification approaches, kernel methods, and neural networks. Topics in unsupervised learning will also be covered if time permits.

College/Department: College of Engineering
Repeat Status: Not repeatable for credit
Prerequisites: ECES 521 [Min Grade: C]

This course emphasizes how to gather data then train, test, and deploy practical machine learning systems using modern software libraries, with an emphasis on Keras on TensorFlow. Complementing the other department courses emphasizing the mathematics behind machine learning algorithms and the ways these can be tailored to specific computing architectures, this project-focused course emphasizes the practice of rapidly prototyping and testing multiple learning structures. To provide the broadest applicability, datasets will range from rich text, to financial time series, to sound, images, and video.

College/Department: College of Engineering
Repeat Status: Not repeatable for credit

System identification and parameter estimation, gradient search, least squares and Neural Networks methods. Closed loop implementation of system learning and self-organizing controllers. Random searching learning systems.

College/Department: College of Engineering
Repeat Status: Not repeatable for credit
Prerequisites: ECES 512 [Min Grade: C]

This course aims to equip engineers with the skills to harness the power of computational data analysis and machine learning techniques, particularly in the realms of experimental science and manufacturing processes. Rather than diving deep into the mathematical foundations of algorithms, the focus here is on providing engineers with the practical knowledge and tool sets required for applying these computational methods in real-world scenarios.

College/Department: College of Engineering
Repeat Status: Not repeatable for credit

This course introduces students to cutting-edge machine learning algorithms and their significant role in contemporary business decision making. It bridges theoretical concepts with practical applications, giving students hands-on experience in applying the principles of predictive analytics. Students will extend their statistical programming expertise while learning to build and evaluate predictive models that address real business challenges.

College/Department: LeBow College of Business
Repeat Status: Not repeatable for credit
Prerequisites: STAT 610 [Min Grade: C]