UT Institute of Computer Science Graduation Theses Topics Registry

Organization

Mobile & Cloud Computing Laboratory

Abstract

TOSCA (Topology and Orchestration Specification for Cloud Applications) is an open-standard language used to describe the topology of cloud-based applications and services and their orchestration. On the other hand, AutoML (Automated Machine Learning) is a process that automates the end-to-end process of applying machine learning to real-world problems. This thesis would focus on further development of ML-TOSCA, a new AutoML integration approach to the TOSCA standard. Incorporating AutoML techniques into TOSCA enables users to automatically generate optimized ML models with the help of cloud applications, which can improve the speed and efficiency of model creation.

The student will further improve the current development by addressing following research challenges:
- Providing in-depth control over pipeline behaviour
- Cross-Platform Compatibility
- Workload distribution over multiple computing instances
Related MS Thesis: https://comserv.cs.ut.ee/ati_thesis/datasheet.php?id=77313
Related papers:
- https://doi.org/10.1016/j.jss.2021.111164
- https://kodu.ut.ee/~dehury/publications/conf/QUDOS-dehury-2020.pdf

Graduation Theses defence year

2023-2024

Supervisor

Chinmaya Dehury

Spoken language (s)

English

Requirements for candidates

Level

Masters

Keywords

 

Name

Chinmaya Kumar Dehury

Phone

E-mail

See more