Pages
- 1
- 2
- document
-
Vellekoop, Joris (author)Deep reinforcement learning presents a compelling approach for the exploration of cluttered 3D environments, offering a balance between fast computation and effective vision-based navigation. Yet, the use of 3D navigation for learning-based information gathering remains largely unexplored. Navigation in 3D space poses the challenge of having an...master thesis 2024
- document
-
Dieters, Sibren (author)New mining and exploration projects have revived across Europe with an increasing demand for critical raw materials driven by the energy transition and unstable political conditions. Hyperspectral imaging proves to be an excellent tool for quick and efficient non-invasive mineral exploration. By mounting hyperspectral- and LiDAR sensors on...master thesis 2023
- document
-
LIAO, DINO (author)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...master thesis 2023
- document
-
Oren, Yaniv (author)Deep, model based reinforcement learning has shown state of the art, human-exceeding performance in many challenging domains. <br/>Low sample efficiency and limited exploration remain however as leading obstacles in the field. <br/>In this work, we incorporate epistemic uncertainty into planning for better exploration.<br/>We develop a low-cost...master thesis 2022
- document
-
MISHRA PARASNATH, PUNITH (author)Diversity as a topic is increasingly becoming important aspect of organizations and society in general. Team diversity could bring different perspectives and thus diverse teams could reap the benefits such as better performance, innovation, and problem-solving abilities. Teams face challenge of deciding between alignment activities focused on...master thesis 2021
- document
-
Tumkur Venkatesh, Aishwarya (author)The study aims to add to the existing knowledge base on individual ambidexterity by adopting a trait-based approach. As this area of individual ambidexterity is still comparatively new, limited study has been undertaken on the internal factors that determine individual ambidexterity. Further the study addresses the degree to which personality...master thesis 2021
- document
-
Changavi Shiva Prasad, Sambhram (author)As a part of JMP at TU Delft, we had the opportunity to design for implementation of sex education in Indonesia. We were unable to explore the culture of Bali together as a design team because of which we had our own assumptions, perceptions of what the culture is or could be. And most importantly in the project we had reduced a whole culture to...master thesis 2021
- document
-
Liu, Yufei (author)Food is of great significance in the lives of Chinese people. In addition to nutrition, it is also closely related to emotions, social interactions, environment, and culture. China's food culture is not only diverse but also developed its own characteristics in various regions. In recent years, the phenomenon of Chinese young people migrating to...master thesis 2021
- document
-
van Roessel, L. (author)Active inference is a process theory arising from neuroscience which casts perception, action, planning and learning under one optimisation criterion: minimisation of free energy. Current literature on the implementation of discrete state-space active inference focuses on scalability, the comparison to reinforcement learning and its performance...master thesis 2020
- document
-
Kwaks, M. (author)This graduation project is about transforming Campus North on the Hembrug terrain in Zaandam as part of the studio Heritage and Architecture. Hembrug is a former military production terrain and was the logistic heart of the “Stelling of Amsterdam”. This area was left vacant since 2003, but in recent years new occupants inhabit Hembrug. The...master thesis 2020
- document
-
Oren, Yaniv (author)Identifying the most efficient exploration approach for deep reinforcement learning in traffic light control is not a trivial task, and can be a critical step in the development of reinforcement learning solutions that can effectively reduce traffic congestion. It is common to use baseline dithering methods such as $\epsilon$-greedy. However,...bachelor thesis 2020
- document
-
Tjong-Ayong, Joseph (author)Public spaces are the places where people come together in the physical environment. They are precious as they have in them the possibility of bringing together people with different cultures and backgrounds. In some cases, however these important spots within our cities are not designed to maximize their capacity for human exploration. As seen...master thesis 2020
- document
-
Dingjan, Mitchell (author)Recommender systems focus on automatically surfacing suitable items for users from digital collections that are too large for the user to oversee themselves. A considerable body of work exists on surfacing items that match what a user liked in the past; this way, the recommender system will exploit its knowledge of a user's comfort zone. However...master thesis 2020
- document
-
van Essen, Anne (author)In recent years, the popularity of compact living spaces like Tiny Houses is rising in the Netherlands. With Tiny Houses still gaining in popularity, there is a demand for information and knowledge about this new form of living. Through multiple sources, interested people are learning about tiny living and how to realize living in a Tiny House....master thesis 2018
- document
-
Cavaliere, Camilla (author)Since 2017 blockchain (BC) has been settling in the spotlight. Several industry fields could use the technology as part of the underlying infrastructure for registering and transferring any type of asset and optimize business processes. As of 2018, numerous blockchain initiatives are continuously developed, with global executives looking forward...master thesis 2018
- document
-
Starre, Rolf (author)Recent Reinforcement Learning methods have combined function approximation and Monte Carlo Tree Search and are able to learn by self-play up to a very high level in several games such as Go and Hex. One aspect in this combination<br/>that has not had a lot of attention is the action selection policy during self-play, which could influence the...master thesis 2018
- document
-
Dubbeld, Maarten (author)Small and Medium-sized Enterprises (SMEs) tend to focus upon short-term profit in a crisis period, however the EU advised SMEs’ to invest in innovation and quality of products. How SMEs balance between these two contradicting strategies is seldom addressed. Therefore, this study explores how SMEs align their organization upon short term...master thesis 2018
- document
-
Keulen, Bart (author)An important problem in reinforcement learning is the exploration-exploitation dilemma. Especially for environments with sparse or misleading rewards it has proven difficult to construct a good exploration strategy. For discrete domains good exploration strategies have been devised, but are often nontrivial to implement on more complex domains...master thesis 2018
- document
-
Roosegaarde Bisschop, D.G. (author)The aim of this thesis study is to increase the geological knowledge on the presence of Heavy Mineral Sands (HMS) in the concession areas owned by Guinea Alluvial Mining (GAM) in Guinea. In order to achieve this aim the following main research question has been formulated: Does exploration of the concession areas show sufficient Heavy Mineral...master thesis 2015
- document
-
Frese, E.M. (author)Unilever, a multinational consumer goods company, intends to improve its exploratory capacity in the front end of its innovation process. Many companies today make use of the Stage-Gate process, as does Unilever. The Stage-Gate process is a controlled phased innovation process which supports management to make decisions on innovation The Stage...master thesis 2014
Pages
- 1
- 2