Enabling Initial and Continuous Cognitive Model Training for Distributed Interdependent Entities
Background & Research Goal
The emergence of smart services in distributed supply network yields manifold opportunities. Companies could create new offerings based on the analysis of data or optimize existing processes. One key method for deriving insights from data is machine learning. To analyze data in smart service systems, many connected machine learning models could analyze distributed data at its source.
However, the initial and continuous training and communication of these models is challenging.
This thesis aims to design, develop and evaluate a method for initializing and continuously improving multiple connected machine learning models.
- have first experience with applying machine learning techniques
- work in an independent and accurate way
- be able to program a prototype and evaluate results (preferably in Python)
We offer you a close supervision and the opportunity to extend your skillset and work on an emerging topic in information systems.
If you are interested, send your CV, transcript of records and a brief description of your skills and motivation to hirt. ∂kit edu