| Professor |
Chrysanthi Kosyfaki
|
| Syllabus |
In the era of data, numerous real-world applications are best represented as
networks. This perspective is vital as analyzing these networks can uncover
valuable insights, extract interesting information, and make informed
decisions. Modern technologies have significantly enhanced our ability to
access vast volumes of data, simplifying and reducing the cost of storage.
Understanding the importance of data is crucial in addressing diverse
challenges, such as traffic congestion, financial network fraud detection,
and the spread of misinformation in social networks, to name a few.
Consequently, there is an increasing necessity to develop advanced tools
that can address these challenges and further understand the importance of
data is more necessary than ever. Examples of these technologies can be
machine learning techniques (e.g., modeling different problems using GNNs),
and natural language processing (NLP) techniques (text preprocessing and
sentiment analysis). |
| Introduction by Professor |
|
| Learning Outcomes |
|
| Pre-requisites |
Very good knowledge of programming (Python
recommended) and knowledge of fundamental data science concepts and
techniques (e.g. linear algebra) |
| Compatibility |
- |
| Topics covered |
|
| Assessment |
|
| Course materials |
|
| Session dates |
|
| Add/drop |
20 January, 2025 - 18 February, 2025 |
| Maximum class size |
150 |