Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 20 for “"Human Preferences"”.
-
Automated image sharpening via supervised learning with human preferences
… through a training set of examples for which human preferences are obtained in psychophysical experiments. The human judgments are also used to learn the function that maps the (sub)space to the best sharpening parameter values. This function thus facilitates adaptive enhancement across an …
-
Terrain Cost Learning from Human Preferences for Robot Path Planning Using a Visual User Interface
… This can be accomplished by leveraging the path preferences of a human operator so that, with selective inputs, the agent can effectively learn a terrain-cost mapping in order to determine the optimal route, thereby eliminating the need for traversal.</p> <p>This thesis aims to achieve this goal …
-
Steerable Alignment with Conditional Multiobjective Preference Optimization
… imperative that these systems are aligned with human preferences. Current state of the art strategies for alignment such as Reinforcement Learning from Human Feedback (RLHF) have provided useful paradigms for finetuning LLMs to produce outputs that are more consistent with human preferences. …
-
Future of Personalized, Aligned Language Models
… Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are effective, but impractical for LLM adaptation due to their high inference cost. …
-
Goal Inference from Open-Ended Dialog
… and accomplish a wide range of user goals and preferences efficiently and robustly. Large Language Models (LLMs) are often used as they allow for opportunities for rich and open-ended dialog type interaction between the human and agent to accomplish tasks according to human preferences. In this …
-
Using Qualitative Preferences to Guide Schedule Optimization
… computers become more capable, we see more mixed human-robot- computer teams. One strategy for coordinating mixed teams is standardizing priorities across agents. However, the encoding of priorities may lead to discrepancies in interpretation across different types of agents. For example, a …
-
Data Acquisition for Enhancing Human-Informed Topology Optimization
… designed for the future development of HumanInformed Topology Optimization (HiTop) towards the deeper integration of optimization and real-world feasibility. Topology optimization produces high-performance designs by optimally distributing material, but its application in professional …
-
Multimodal Indexing of Presentation Videos
… we detect, track, match, and finally select a humanly preferred face icon per speaker, based on three quality measures: resolution, amount of skin, and pose. We register a 87% accordance (51 out of 58 speakers) between the face indexes automatically generated from three unstructured …
-
Aligning Language Models Using Multi-Objective Deep Reinforcement Learning
… techniques is reinforcement learning from human feedback (RLHF). RLHF aims to optimize one objective based on human preferences. However, the cost of high-quality human feedback is enormous. Having all human annotators consistent in their opinions on desirable behaviors is also challenging. …
-
ECOLOGICAL AND SOCIETAL IMPACTS OF SUBURBAN WHITE-TAILED DEER: A CASE STUDY IN THE CHICAGO METROPOLITAN AREA
… populations, deer impacts on vegetation, and human preferences toward deer and deer management to support decision making. My study based in the Chicago Metropolitan Area during 2007-2011, utilized a multi-faceted approach to investigate common obstacles in suburban deer management. In my …
-
Examining LLMs in Economic Settings
Humans are not homo economicus (i.e., rational economic beings). We exhibit systematic behavioral biases such as loss aversion, anchoring, framing, etc., which lead us to make suboptimal economic decisions. Insofar as such biases may embedded in text data on which large language models (LLMs) are …
-
Anytime information theory
… of differentiated service without appealing to human preferences.
-
Designing green stormwater infrastructure for hydrologic and human benefits: an image based machine learning approach
… green spaces are also major contributors to human health. Considerable research in the psychological sciences have shown significant human health benefits from appropriately designed green spaces, yet impacts on human wellbeing have not yet been formally considered in GI design frameworks. …
-
Communication-Driven Robot Learning for Human-Robot Collaboration
… design, as these robots must learn skills from human inputs. Two main components close the loop in a human-robot interaction: learning and communication. Learning derives robot behaviors from human inputs, and communication conveys information about the robot's learning to the human. This …
-
LEARNING STRUCTURED ALIGNMENT: FROM VISUAL UNDERSTANDING TO ROBOT CONTROL
… demonstrating effective alignment between human preferences and robot behaviors even under high noise conditions.
-
Anticipating, Extracting, and Leveraging Information in Clinical Decision-Making
… understanding - as opposed to merely imitating - human decision-making. We introduce two novel models: interpretable policy learning (Interpole), which explains human actions through decision dynamics and decision boundaries, and lexicographically-ordered reward inference (LORI), which explains …
-
Exploring the factors affecting employee motivation to be innovative on product development: A case study for Woolworths South Africa
… industry is greatly affected by revolutionised human knowledge that requires a continued understanding of human preferences, needs and wants. Motivation to innovate must be understood when marketers aim for business success. Business success is seen in customer satisfaction and employee …
-
Data-Driven Design Framework for Hybrid Workspaces
… well as organisational interests and individual preferences. The COVID-19 pandemic has accelerated the evolution of office design through a forced large-scale ‘work from home’ experiment. In the post-pandemic time, the conventional ‘office’ concept is being reconsidered as advanced digital …
-
Dirbtinio intelekto potencialas rinkimuose /
… main objective: people do not know their true preferences, only what information they declare themselves. In this way, elections become vulnerable and inaccurate, which undermines the integrity and credibility of elections, because they do not effectively reveal the preferences of voters. The …
-
Health-related quality of life and disease burden of psoriasis in Iran
… changing by rise of new needs and diversity in human preferences. Also by improvement of life expectancy from the beginning of 20th century, the concept of health for the person and the society has evolved. Advancements in science and technology has made this possible and has changed human …