Machine Learning for Time Series Data (Sommersemester 2023)

Dozent: Dr. Tim Januschowski (Artificial Intelligence and Sustainability) , Dr. Jan Gasthaus (Artificial Intelligence and Sustainability)

Allgemeine Information

• Semesterwochenstunden: 2
• ECTS: 3
• Benotet: Ja
• Einschreibefrist: 01.04.2023 - 07.05.2023
• Lehrform: Projektseminar
• Belegungsart: Wahlpflichtmodul
• Lehrsprache: Englisch

Studiengänge, Modulgruppen & Module

Beschreibung

Machine Learning is used in many companies for core business functions where numerical time series (e.g., demand for an online retailer, staff attendance, telemetry data from cloud resources) are ubiquitous. Accordingly, the interest in adapting and innovating machine learning methods that handle time series (i.e. data that exhibit temporal dependencies, going beyond the standard IID assumption) natively is growing. Common ML tasks that are addressed using time series data include forecasting, anomaly detection, time series classification, representation learning, and missing value imputation. Furthermore, challenges common to the entire ML community like causality or interpretability often need non-trivial adaptations to the time series setting.

In this seminar we will select and discuss topics of current research in machine learning for time series. This seminar will let students get acquainted with current machine learning research, let them explore new fields and ideas and let them analyze and criticize recent publications.

To do so, we will offer students to either go broad or deep: for the broad option, students will select a group of research papers (2-5) from a curated list, covering different approaches and perspectives on a particular task, which they should carefully read, analyze, and critically evaluate. Starting from these they should explore the surrounding literature and summarize their findings, criticism, and research ideas in a 4-page paper (double column). For the deep option, students will select a single paper which has code available and dive more deeply into the particular method, and explore it both theoretically as well as practically, e.g., by comparing it to another, potentially missing baseline or making modifications (e.g., making a point estimator probabilistic). For either the broad or the deep scenario, all students will prepare 25-minute presentations and present their work during a block seminar at the end of the semester.

Goals of the Course

Understand...

• opportunities and challenges arising from modern time series data

Do ...

• work alone or in small teams
• read and scrutinize recent literature
• implement models in open source (GluonTS)

Improve/Learn ...

• mathematical, analytical, and modeling skills
• deep learning and probabilistic modeling skills

Voraussetzungen

• interest in quantitative methods, machine learning and statistics
• programming skills/experience
• the number of participants is not restricted

Literatur

• Gentle Introduction to Forecasting
• Recent Overview of forecasting methods

Lern- und Lehrformen

The course is a combination of a lecture and a practical part:

• teachers impart relevant knowledge and methods
• students work on a topic either alone or in a team of up to 3 people
• students present and document their work

HPI Moodle course: https://moodle.hpi.de/course/view.php?id=462

Leistungserfassung

Portfolio assessment for students consisting of:

1. final presentation of project results 
2. project documentation at the end of the module

Termine

During the first 4 weeks, the course will consist of lectures that will provide an introduction into time series, evaluation metrics for forecasting and classical & modern methods. Afterwards, we will choose papers/manuscripts which the students will then work on on their own or in teams. The lectures will be replaced with office hours and at the end of the course, we will spend 1-2 days together (depending on the number of participants) for the presentations of the results.

Zurück