Course taught in the Data and Knowledge 2nd year Master Program of Université Paris Saclay 2018-2019
The Internet of Things (IoT) is producing huge quantities of data in real-time as data streams. Data stream mining or Real-Time Analytics relies on and develops new incremental algorithms that process streams under strict resource limitations.
This course focuses on, as well as extends the methods implemented in open source tools as MOA. Students will learn to how select and apply an appropriate method for a given data stream problem; they will learn how to design and implement such algorithms; and they will learn how to evaluate and compare different solutions.
Lecturers: Jesse Read and Albert Bifet
Evaluation:
- 10% Lab Assignments
- 30% Project
- 60% Final Test
Lecture Slides
- 1. Classification in Data Streams Slides
- 2. Introduction Slides
- 3. Stream Algorithmics Slides
- 4. Concept Drift Slides
- 5. Evaluation Slides
- 6. Ensembles Slides
- 7. Time Series and Sequential Data Slides
- 8. Clustering Slides
Session Labs
- 1. Lab Massive Online Analysis (MOA) Lab – Submission (due 12 December 2019)
- 2. Lab Sckit-multiflow I Lab – Submission (due 9 January 2019)
- 3. Lab Sckit-multiflow II Lab – Submission (due 23 January 2019)
Projects
Propose teams and rank topics by Wednesday 12/12/18: Projects
References
Book Machine Learning for Data Streams.