A Step Towards Understanding Normalizing Flows and their Likelihood Behavior

Normalizing flows have demonstrated their ability to learn complex and high-dimensional distributions. However, the behavior of normalizing flow likelihoods are not yet fully understood, particularly when exposed to outlier data, where it has been observed that large likelihoods are often assigned to inputs that are substantially different from...

A generative AI integration tool for managers: Preparing, dealing and thriving with the impact of AI

This graduation report presents a comprehensive approach to the identification of an opportunity in the rising technology and interests in generative AI. The report delivers a concept for a tool that is designed for managers. The tool is aimed at aiding in the integration of generative AI within teams. The project is grounded in a literature...

Computational Design in Industrial Design: An Initial Investigation

The project aims to understand the relationship between Computational Design (CD) and Industrial Design (ID) and to investigate future scenarios for CD adoption. CD can be defined as a shift in design representation and thinking, that has significant implications for the design process and its outcome. With CD, machines become active...

Exploring Hybrid Intelligence for Topic Interpretation in Colorectal Cancer Research: A Comparative Study of GPT-3.5 and Human Expertise

Colorectal cancer is a widespread disease that significantly impacts the health of individuals worldwide. Understanding the needs and concerns of those affected by this disease is crucial for improving patient outcomes and enhancing the quality of care. Patient web forums have emerged as valuable platforms for individuals to openly share their...

PLAI: Positive Implementation of Generative AI in Education Through Play-Based Learning

Generative AI has had a profound impact on various sectors since mid-2022. The rapid adoption by students poses challenges for student assessment and raises concerns about student development. This thesis delves into the subject and proposes a positive implementation in education through play-based learning. The project uses a human-centred...

Designing for explanation-driven trust in Chatbots

Trust plays an important role in the implementation of chatbot technology. This study was also focusing on user trust in chatbots, particularly focusing on the role of response delay and explanation-driven driven subjective transparency. This research includes a pretest and a main test. In the pretest, we selected one explanation that was...

Aesthetics in Visual Training Datasets

Correctly processing accumulated information is beneficial for our survival. Berghman and Hekkert (2017) argue that this is why we humans derive pleasure from having a sense of aesthetics. These aesthetic experiences can be seen as our brain’s reward system for correctly perceiving and interpret- ing the world around us. While our senses have...

Generative AI & Tangible Products: Human-AI Design of 3D-printed Lamps

New generative AI systems can make beautiful pictures, but can they help produce functional products? This graduation project investigated the potential for generative AI to aid the design of functional, 3D-printed lamps. <br/>Two studies were conducted to assess the degree to which AI can measurably improve design outputs. An AI-based software...