This course will cover modern and deep neural networks with a focus on how they can be correctly implemented and applied to a wide range of data types. It will cover the backpropagation algorithm and how it is used and extended for deep feedforward, recurrent and convolutional neural networks. An emphasis will be placed on the implementation, design, testing and training of neural networks. The course will also include an introduction to using a modern neural network framework.

Hallmarks of AI include systems that exhibit human-like behaviors, and AI systems rely on continuous preparation and deployment of data resources as new tasks emerge. In this course, students develop their conceptual, applied, and critical understanding about (1) a full life cycle of conducting AI research; (2) experimental design and statistical methods to collect and validate data resources and conduct computational experiments in AI system development and deployment; (3) human-centered AI concepts and techniques, (4) best practices for technical writing and presentation about AI, and (5) concepts and methods for responsible, fair, and explainable AI. Based on research review, students write and present an experimental design proposal spanning dataset elicitation and computational experimentation, including description and visualization of the experiment and critical reflection on the benefits, limitations, and implications for AI system development and deployment.

This course provides the student with an opportunity to explore a project-based research experience that advances knowledge in that area. The student selects a research problem, conducts background research, develops the system, analyses the results, and builds a professional document and presentation that disseminates the project. The report must include an in-depth research report on a topic selected by the student and in agreement with the student's adviser. The report must be structured as a conference paper, and must be submitted to a conference selected by the student and his/her adviser.

This course provides the student with an opportunity to complete their capstone project, if extra time if needed after enrollment in SWEN-790. The student continues to work closely with his/her adviser.