Course home

Syllabus and Projects

 

 

---

---

Assignments (Each student finishes each assignment alone)

1. Data processing and visualization: 10%

2. Log Anomaly Detection: 20%

Project (A team of 2-3 students finish the project together)

3. Time Series Anomaly Detection  Competition from  AIOps Challenge: 60%

Syllabus:

Week	Date	Topic, Papers, Slides and Reading List	Algorithms & Techniques
1	Sep 11 (9:50-12:15)	Course Introduction
2	Sep 18 (9:50-12:15)	Video streaming	Data Visualization Correlation, Regression, Information gain, Decision trees, Regression trees
3	Sep 25 (9:50-12:15)
4	Oct 2 (No Class due to school holidays)
5	Oct 2 (No Class )
6	Oct 16 (9:50-12:15)	KPI Anomaly detection	Time series Algorithms. Random Forests Deep Generative Models (VAE & GAN) Clustering Similarity
7	Oct 23 (9:50-12:15)
8	Oct 30 (9:50-12:15)	Log Anomaly Detection	Learning From Text CNN Deep Sequence Learning
9	Nov 6 (9:50-12:15)
10	Nov 13 (9:50-12:15)	Anomaly Localization	Monte Carlo Tree Search
11	Nov 20 (9:50-12:15)	Event/Failure Prediction	Regularization SVM Transfer Learning Extreme Gradient Boosted Trees
12	Nov 27 (9:50-12:15)	Resource Management	Deep Reinforcement Learning
13	Dec 4 (9:50-12:15)	Operations Knowledge Graph	Association Mining  Causal Inference Knowledge Graph
14	Dec 11 (9:50-12:15)
15	Dec 18 (9:50-12:15)
16	Dec 25 (9:50-12:15)	Project Presentation