Browsing Theses and Dissertations(library) by Author "Huber, Manfred"
Now showing items 41-60 of 63
-
LEARNING PERCEPTION TO ACTION MAPPING FOR FUNCTIONAL IMITATION
Singh, Bhupender (2016-12-09)Imitation leaning is the learning of advanced behavior whereby an agent acquires a skill by observing another's behavior while performing the same skill. The main objective of imitation learning is to make robots usable ... -
Learning Representations Using Reinforcement Learning
Bose, Sourabh; 0000-0002-1504-8942 (2019-05-09)The framework of reinforcement learning is a powerful suite of algorithms that can learn generalized solutions to complex decision making problems. However, the applications of reinforcement learning algorithms to traditional ... -
Learning State And Action Space Hierarchies For Reinforcement Learning Using Action-Dependent Partitioning
Asadi, Mehran (Computer Science & Engineering, 2007-08-23)Autonomous systems are often dicult to program. Reinforcement learning (RL) is an attractive alternative, as it allows the agent to learn behavior on the basis of sparse, delayed reward signals provided only when the ... -
LEARNING TO GENERATE INDIVIDUAL DATA SEQUENCE FROM POPULATION STATISTICS USING DYNAMIC BAYESIAN NETWORKS
Qureshi, Mohammed Azmat; 0000-0002-0865-4733 (2018-05-11)Data collection rose exponentially with the dawn of the 21st Century, However the most important data to humans, individual health data, is difficult to get approved for public research, as medical history is very sensitive ... -
LEARNING TRANSFERABLE META-POLICIES FOR HIERARCHICAL TASK DECOMPOSITION AND PLANNING COMPOSITION
Djurdjevic, Predrag (2019-12-16)In real world scenarios where situated agents are faced with dynamic, high-dimensional, partially observable environments with action and reward uncertainty, the traditional states space Reinforcement Learning (RL) becomes ... -
MACHINE LEARNING METHODS TO IMPROVE FAIRNESS AND PREDICTION ACCURACY ON LARGESOCIALLY RELEVANT DATASETS
Jain, Bhanu Chaturvedi (2021-08-16)Machine learning-based decision support systems bring relief to the decision-makers in many domains such as loan application acceptance, dating, hiring, granting parole, insurance coverage, and medical diagnoses. These ... -
Multiple Object Tracking Using Particle Filters
Ryu, Hwangryol (Computer Science & Engineering, 2007-08-23)We describe a novel extension to the Particle filter algorithm for tracking multiple objects. The recently proposed algorithms and the variants for multiple object tacking algorithms estimate multi-modal posterior distributions ... -
Neural Image and Video Understanding
Fakoor, Rasool (2017-08-25)Even though recent works on neural architectures have shown promising results at tasks like image recognition, object detection, playing Atari games, etc., learning a mapping from a visual space to a language space or vice ... -
Neural Network Architecture Optimization Using Reinforcement Learning
Vadhera, Raghav; 0009-0006-0679-3904 (2023-05-19)Deep learning has emerged as an increasingly valuable tool, employed across a myriad of applications. However, the intricacies of deep learning systems, stemming from their sensitivity to specific network architectures, ... -
On-Line Environment Adaptation for User Performance Optimization
Sarkar, Subharag (2023-08-14)In today’s fast-paced and globally connected world, businesses are creating products with more significance to user personalization and customization. This has amplified the importance of capturing and learning user ... -
PERSON IDENTIFICATION AND ANOMALY DETECTION USING GAIT PARAMETERS EXTRACTED FROM TIME SERIES DATA
Rama Krishna Reddy, Suhas Mandikal; 0000-0002-0434-4105 (2017-05-31)Gait generally refers to the style of walk and is influenced by a number of parameters and conditions. In particular, chronic and temporary health conditions often influence gait patterns. As such conditions increase with ... -
PERSON IDENTIFICATION AND TINETTI SCORE ASSESSMENT USING BALANCE PARAMETERS TO DETERMINE FALL RISK
Chawan, Varsha Rani; 0000-0002-1514-5830 (2020-09-03)This thesis is aimed at a substantial health problem among the elderly population that is “Fall”, a major cause of accidental home deaths. Studies show approximately one-third of community-dwelling people over 65 years of ... -
Predicting Human Behavior Based on Survey Response Patterns Using Markov and Hidden Markov Models
Pokharna, Arun Kumar; 0000-0003-1057-4895 (2016-12-09)With technological advancements in World Wide Web (www), connecting with people for gathering information has become common. Among several ways, surveys are one of the most commonly used way of collecting information from ... -
PROBABILISTIC RISK ASSESSMENT AND THE PATH PLANNING OF SAFE TASK-AWARE AUTONOMOUS RESILIENT SYSTEMS (STAARS)
Kaya, Uluhan Cem; 0000-0003-4054-7994 (2019-05-16)Recent advancements on the unmanned systems manifest the potential of these technologies to impact our daily life. In particular, the unmanned aircraft systems (UAS) become ordinary for people in almost any area from aerial ... -
Pseudo-hierarchical Ant-based Clustering Using A Heterogeneous Agent Hierarchy And Automatic Boundary Formation
Brown, Jeremy Bernard (Computer Science & Engineering, 2009-09-16)The behavior and self-organization of ant colonies has been widely studied and served as the inspiration and source of many swarm intelligence models and related clustering algorithms. Unfortunately, most models that ... -
Randomized and Evolutionary Approaches to Dataset Characterization, Feature Weighting, and Sampling in K-Nearest Neighbors
Basak, Suryoday; 0000-0002-1982-1787 (2020-06-05)K-Nearest Neighbors (KNN) has remained one of the most popular methods for supervised machine learning tasks. However, its performance often depends on the characteristics of the dataset and on appropriate feature scaling. ... -
Reactive Control Composition For Mobile Manipulators
Mathew, Binu George (Computer Science & Engineering, 2010-07-19)A mobile manipulator is a manipulator mounted on a mobile platform. Due to this combination it has increased mobility compared to a fixed manipulator and increased dexterity compared to a mobile platform. At the same time ... -
Reducing The Complexity Of Reinforcement Learning In POMDPs By Decomposition Into Decision And Perceptual Processes
Fakoor, Rasool (Computer Science & Engineering, 2013-03-20)Markov Decision Processes (MDPs) and Partially Observable Markov Decision Processes (POMDPs) are very powerful and general frameworks to model decision and decision learning tasks in a wide range of problem domains. As a ... -
REPRESENTATION AND STRATEGY LEARNING FOR VARIABLE-SIZE TREE TRANSFORMATION USING REINFORCEMENT LEARNING
Hosseini Shirvani, Shirin (2021-08-12)Trees as acyclic graphs are ubiquitous in representing different context where they encode connectivity patterns at all scales of organization, from biological systems to social networks. Trees are powerful resources which ... -
ROBOTICS CURRICULUM FOR EDUCATION IN ARLINGTON: Experiential, Simple and Engaging Learning Opportunity for Low-Income K-12 Students
Vasanthakumar, Sharath; 0000-0003-3233-4825 (2016-05-10)Engineering disciplines (such as biomedical, civil, computer science, electrical, mechanical) are instrumental to society’s wellbeing and technological competitiveness; however the interest of K-12 American students in ...