Stony Brook University 3 credits ESE
This course focuses on different kinds of representation learning algorithms for time series data, under label sparsity, which is a common and fundamental challenge in many application domains. Topics include the common types and characteristics of time series data, important applications such as healthcare, finance and environment; unsupervised, self-supervised and semi-supervised representation learning approaches and strategies including clustering, generative, reconstruction, contrastive, and hybrid ones; and downstream tasks after representation learning such as classification, anomaly detection, forecasting, and imputation. 3 credits Prerequisite: ESE 577 OR ESE 588 OR ESE 589 OR ESE 388 OR CSE 352 OR CSE 353 OR CSE 354 OR instructor approval Grading Letter graded (A, A-, B+, etc.)
Our subject experts help with essays, research papers, case studies, discussion posts, and capstone projects for these programs β written from scratch to your course requirements.
Program and course information is reproduced from each university's published academic catalog for informational purposes and may change. Always confirm current requirements with your university. We are an independent academic support service and are not affiliated with or endorsed by the universities listed.
Expert guides on essay writing, citation styles, study skills, and academic success.
View All Articles
Learn how to write a good research question for a paper. Narrow your topic, identify a research problem, and create a focused question with practical examples.
Learn how to choose a research topic you can actually research. Discover how to narrow broad ideas, find reliable sources, and develop a focused research question.
Learn how to cite sources in a research paper using APA, MLA, and Chicago styles, with in-text citation examples and reference-list tips.