Kategorie: ‘Theses’

An Empirical Study of Open Source Large Language Models (OSLLMs)

November 20th, 2023 | by

Open Source Software (OSS) revolutionised the computing world about three decades ago. One of the principles of OSS guarantees software developers, companies, researchers, and students the freedom to change and improve the software. Characterised by active community involvement (bazaar-style software development), OSS development has produced category-killer Operating Systems (e.g., Debian, Ubuntu) and applications (e.g., the Apache HTTP Server, Firefox). 

The computer science community is now riding another revolution called the Large Language Models (LLMs) revolution. Various variants of LLMs (Commercial and Open Source) come with billions of parameters that developers can fine-tune to control how the system generates text (tokens). Commercial LLMs (e.g., ChatGPT) come with a copyright and are expensive to deploy and use. They have also been criticised for their hallucination, lack of transparency, and the potential for monopolisation by big corporations.

Research methodology

Building a Social Bot for Self-Regulated Learning: Leveraging xAPI Statements, Visualizing Progress, and Recommending Learning Materials

November 17th, 2023 | by

This thesis aims to develop a social bot designed to enhance self-regulated learning experiences by leveraging xAPI statements to track learning progress. The system will employ the “GRETA Kompetenzbilanz” model to visualize the learner’s progress comprehensively, recommend suitable learning materials, and facilitate reflective practices. The project also explores the potential integration of FAQ handling and considers the implementation of MLOps for continuous improvement through retraining of recommendation models.

Algorithmic Approaches to Overlapping Community Detection – Multiplex Network Compatibility and a Chatbot Environment

November 9th, 2023 | by

Psychometrics of AI Dictators: Creating and Analyzing LLM Criminal Personas

November 9th, 2023 | by

Psychometric inventories provide a means to analyze the expression of a variety of human traits. When applied on specific sets of people, they may show shared characteristics that could contribute to their behavior. Common traits can be significant for criminal individuals, as they could be used to discern early warning signs or identifiers. For example, certain profiles of the Dark Triad psychometric test which is composed of psychopathy, machiavellianism, and narcissism, and self-control, have been related to antisocial and criminal externalizing outcomes. In this thesis, we explore the idea of applying psychometrics to generative LLMs that impersonate well-known criminals and dictators to circumvent problems of limited/restricted access to actual, and often historic, people.

Algorithmic Approaches to Overlapping Community Detection – PSO_LPA and Graph Visualization

October 25th, 2023 | by

Rule-Driven Feedback Engine for Psychomotor Learning: From Motion Distance to Error Detection

October 19th, 2023 | by

This master’s thesis aims to advance the field of psychomotor learning within the context of Project MILKI-PSY, a research initiative focusing on multimodal immersive mentoring to facilitate Self-Regulated Learning (SRL) for psychomotor training. Psychomotor learning involves the acquisition of skills through the integration of physical and cognitive processes. In this project, we are developing an innovative framework that leverages immersive technologies to enhance SRL, offering a unique opportunity to revolutionize the way individuals acquire psychomotor skills.

Enhancing Knowledge Graph Embedding with Uncertainty Modeling using Fuzzy Logic

October 16th, 2023 | by

Enhancing Physical Activity and Social Interaction through Peer-assisted Exergames

October 16th, 2023 | by

This bachelor thesis aims to explore the development of a peer-assisted exergame using Unity as the framework and YOLOv8 for movement tracking. Exergames, which combine exercise and gaming elements, have gained popularity in recent years as a means to promote physical activity. However, they often lack a social component, which could enhance motivation and engagement. This research project seeks to address this gap by creating a peer-assisted exergame that encourages players to exercise together while having fun.

Towards a Data Space for Cyber Threat Intelligence

October 13th, 2023 | by

Image stream anomaly detection using feature sketch for industrial quality control

October 4th, 2023 | by