Index Catalog // Hyrax

Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

O Criador:: Desai, Saurabh Satish
Abstract:: Top-performing approaches to embodied AI tasks like point-goal navigation often rely on training agents via reinforcement learning over tens of millions (or even billions) of experiential steps – learning neural agents that map directly from visual observations to actions. In this work, we question whether these extreme training durations are...
Resource Type:: Masters Thesis

A Distributed Scheme for Accelerating and Scaling PSPNet

O Criador:: Krishna, Ajay
Abstract:: Advances in deep learning based image processing have led to their adoption for a wide range of applications, and in tow with these developments is a dramatic increase in the availability of high quality datasets. With this comes the need to accelerate and scale deep learning applications in order to...
Resource Type:: Masters Thesis

Re-understanding Finite-State Representations of Recurrent Policy Networks

O Criador:: Danesh, Mohamad H.
Abstract:: We propose an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM) and then analyzing the equivalent minimized FSM. While this led to interesting insights, the minimization process can obscure a deeper understanding...
Resource Type:: Masters Thesis

A Benchmarking Study of Unsupervised Anomaly Detection Algorithms

O Criador:: Emmott, Andrew F.
Abstract:: It is common practice in the unsupervised anomaly detection literature to create experimental benchmarks by sampling from existing supervised learning datasets. We seek to improve this practice by identifying four dimensions important to real-world anomaly detection applications --- point difficulty, clusteredness of anomalies, relevance of features, and relative frequency of...
Resource Type:: Masters Thesis

ThreshKnot: Thresholded ProbKnot for Improved RNA Secondary Structure Prediction

O Criador:: Zhang, Liang
Abstract:: RNA structure prediction is a challenging problem, especially with pseudoknots. Recently, there has been a shift from the classical minimum free energy-based methods (MFE) to partition function-based ones that assemble structures based on base-pairing probabilities. Two typical examples of the latter group are the popular maximum expected accuracy (MEA) method...
Resource Type:: Masters Thesis

Long Wave Amplification in a Coral-Reef Lagoon

O Criador:: Bheeroo, Vivek Anand
Abstract:: A series of laboratory experiments were conducted to study the wave field in the inner lagoon excited by ‘long’ incident waves. Three cases were considered: Cases A, B and C presenting incident waves of wavelength with factors of 1, 2 and 2.5 times the width of the reef respectively. The...
Resource Type:: Masters Thesis

Assisting Sustainability Analysis of Forest Bioenergy Supply Chains using Mathematical Optimization

O Criador:: Sadeghi, Javad
Abstract:: Changes in the global climate and forest management practices have given rise to increasing numbers and severity of wildfires. More than five million acres burned in the United States in 2017, while in Canada 7.4 million acres burned. In particular, an increasing amount of dead woody biomass is a key...
Resource Type:: Masters Thesis

Event detection with forward-backward recurrent neural networks

O Criador:: Ghaeini, Mohammad Reza
Abstract:: Automatic event extraction from natural text is an important and challenging task for natural language understanding. Traditional event detection methods heavily rely on manually engineered rich features. Recent deep learning approaches alleviate this problem by automatic feature engineering. But such efforts, like tradition methods, have so far only focused on...
Resource Type:: Masters Thesis

An Investigation on Nanoscale-shape-mediated Coupling Between Temperature and Densification in Intense Pulsed Light Sintering of Silver Nanoparticles

O Criador:: Bansal, Shalu
Abstract:: In Intense Pulsed Light (IPL) sintering, pulsed large-area visible light from a xenon lamp is absorbed by nanoparticle films or patterns and converted to heat, resulting in rapid sintering of the nanoparticles. This work experimentally characterizes IPL sintering of silver nanoparticle films. A newly observed turning point in the evolution...
Resource Type:: Masters Thesis

Using Change Representations to Analyze Properties of Variational Software

O Criador:: Wang, Xiangyu
Abstract:: Appropriate representations of variational software simplify the analysis of their properties.This thesis proposes tailored representations of two kinds variational softwares: difference files of merge commits in Git and feature models. For the former, we use the Choice Edit Model, which is based on the choice calculus, to represent changes introduced...
Resource Type:: Masters Thesis

D₊₊ : Structural Credit Assignment in Tightly Coupled Multiagent Domains

O Criador:: Rahmattalabi, Aida
Abstract:: Autonomous multiagent teams can be used in complex exploration tasks to both expedite the exploration and improve the efficiency. However, use of multiagent systems presents additional challenges. Specifically, in domains where the agents' actions are tightly coupled, coordinating multiple agents to achieve cooperative behavior at the group level is difficult....
Resource Type:: Masters Thesis

OME : A Framework for Running Spatially Explicit System Dynamics Models

O Criador:: Wingo, Patrick C.
Abstract:: The Open Modeling Environment (OME) is a tool developed to address some known shortcomings in ecological System Dynamics (SD) modeling research. OME provides a common set of methods for interacting directly with spatial information, reducing the need for modelers to create their own methods for doing so. The environment is...
Resource Type:: Masters Thesis

Learning-based Control of Experimental Hybrid Fuel Cell Power Plant

O Criador:: Gabler, Andrew
Abstract:: Direct red Solid Oxide Fuel Cell (SOFC) Turbine hybrid plants have the potential to dramatically increase power plant efficiency, decrease emissions, and provide fast response to transient loads. The US Department of Energy's (DOE) Hybrid Performance Project is an experimental hybrid SOFC plant, built at the National Energy Technology Laboratory...
Resource Type:: Masters Thesis

Evaluation of Parallel Monte Carlo Tree Search Algorithms in Python

O Criador:: Jothi, Shankar
Abstract:: Monte-Carlo Tree Search (MCTS) is an online-planning algorithm for decision-theoretic planning in domains with stochastic and combinatorial structure. The general applicability of MCTS makes it an ideal first choice to investigate when developing planners for complex applications requiring automated control and planning. The first contribution of this thesis is to...
Resource Type:: Masters Thesis

Offensive Direction Inference in Real-World Football Video

O Criador:: Lu, Qingkai
Abstract:: Automatic analysis of American football videos can help teams develop strategies and extract patterns with less human effort. In this work, we focus on the problem of automatically determining which team is on offense/defense, which is an important subproblem for higher-level analysis. While seemingly mundane, this problem is quite challenging...
Resource Type:: Masters Thesis

Data Collection in Sensor Networks via the Novel Fast Markov Decision Process Framework

O Criador:: Duong, Thai
Abstract:: We investigate the data collection problem in sensor networks. The network consists of a number of stationary sensors deployed at different sites for sensing and storing data locally. A mobile element moves from sites to sites to collect data from the sensors periodically. There are different costs associated with the...
Resource Type:: Masters Thesis

Pedestrian distraction : pedestrian behaviors at midblock crossings considering geometric and environmental conditions

O Criador:: Kautz, Julia Anne
Abstract:: Pedestrian distraction at roadway crossings has been correlated with a higher risk of pedestrian-vehicle collisions due to the pedestrian's cognitive, visual, and motor attention being drawn to a wide variety of secondary tasks. This study is different from previous field studies of pedestrian midblock crossings in that the geometric layout...
Resource Type:: Masters Thesis

A study on student perceptions of principles of logic and their application to the principle of mathematical induction

O Criador:: Boone, Allan R.
Abstract:: The purpose of this article is to explore student reasoning with regard to problems in logic, particularly those related to the Principle of Mathematical Induction (PMI). The five case studies presented build off of work done by other researchers, most notably Dubinsky and Harel, who both looked at how students'...
Resource Type:: Masters Thesis

Learning greedy policies for the easy-first framework

O Criador:: Xie, Jun
Abstract:: Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
Resource Type:: Masters Thesis

Reinforcement learning-based off-equilibrium incentives to approximate the VCG mechanism

O Criador:: Moissinac, Béatrice
Abstract:: Auctions are used to solve resource allocation problem between many agents and many items in real-world settings. Unfortunately, in most cases, it is possible for selfish agents to manipulate the system for their own interest at the expense of the social welfare. Such manipulation can be prevented using the Vickrey-Clarke-Groves...
Resource Type:: Masters Thesis

Physical activity recognition of free-living data using change-point detection algorithms and hidden Markov models

O Criador:: Anderson, Michael M.
Abstract:: Physical activity recognition using accelerometer data is a rapidly emerging ﬁeld with many real-world applications. Much of the previous work in this area has assumed that the accelerometer data has already been segmented into pure activities, and the activity recognition task has been to classify these segments. In reality, activity...
Resource Type:: Masters Thesis

Adiabatic Markov Decision Process : convergence of value iteration algorithm

O Criador:: Duong, Thai
Abstract:: Markov Decision Process (MDP) is a well-known framework for devising the optimal decision making strategies under uncertainty. Typically, the decision maker assumes a stationary environment which is characterized by a time-invariant transition probability matrix. However, in many real-world scenarios, this assumption is not justified, thus the optimal strategy might not...
Resource Type:: Masters Thesis

Using RUBI to partition agents in air traffic problems with hard constraints and reward shaping

O Criador:: Curran, William
Abstract:: Air traffic flow management over the U.S. airpsace is a difficult problem. Current management approaches lead to hundreds of thousands of hours of delay, costing billions of dollars annually. Weather and airport conditions may instigate this delay, but routing decisions balancing delay with congestion contribute significantly to the propagation of...
Resource Type:: Masters Thesis

Active learning of constraints for semi-supervised clustering

O Criador:: Xiong, Sicheng
Abstract:: Semi-supervised clustering aims to improve clustering performance by considering user supervision in the form of pairwise constraints. In this paper, we study the active learning problem of selecting pairwise must-link and cannot-link constraints for semisupervised clustering. We consider active learning in an iterative manner where in each iteration queries are...
Resource Type:: Masters Thesis

Investigation of automatic construction of reactive controllers

O Criador:: Westerberg, Caryl J.
Abstract:: In real-time control systems, the value of a control decision depends not only on the correctness of the decision but also on the time when that decision is available. Recent work in real-time decision making has used machine learning techniques to automatically construct reactive controllers, that is, controllers with little...
Resource Type:: Masters Thesis

High-speed implementation of the RSA cryptosystem

O Criador:: Peng, Yanqun
Abstract:: A public key cryptosystem allows two or more parties to securely communicate over an insecure channel without establishing a physically secure channel for key exchange. The RSA cryptosystem is the most popular public key cryptosystem ever invented. It is based on the difficulty of factoring large composite numbers. Once the...
Resource Type:: Masters Thesis

A numerical approach to Tamme's problem in euclidean n-space

O Criador:: Adams, Patrick Guy
Resource Type:: Masters Thesis

Exploring the impact of test suite granularity and test grouping technique on the cost-effectiveness of regression testing

O Criador:: Qiu, Xuemei
Abstract:: Regression testing is an expensive testing process used to validate changes made to previously tested software. Different regression testing techniques can have different impacts on the cost-effectiveness of testing. This cost-effectiveness can also vary with different characteristics of test suites. One such characteristic, test suite granularity, reflects the way in...
Resource Type:: Masters Thesis

Shrunken learning rates do not improve AdaBoost on benchmark datasets

O Criador:: Forrest, Daniel L. K.
Abstract:: Recent work has shown that AdaBoost can be viewed as an algorithm that maximizes the margin on the training data via functional gradient descent. Under this interpretation, the weight computed by AdaBoost, for each hypothesis generated, can be viewed as a step size parameter in a gradient descent search. Friedman...
Resource Type:: Masters Thesis

Adversarial planning by strategy switching in a real-time strategy game

O Criador:: King, Brian D.
Abstract:: We consider the problem of strategic adversarial planning in a Real-Time Strategy (RTS) game. Strategic adversarial planning is the generation of a network of high-level tasks to satisfy goals while anticipating an adversary's actions. In this thesis we describe an abstract state and action space used for planning in an...
Resource Type:: Masters Thesis

Object highlighting : real-time boundary detection using a Bayesian network

O Criador:: Jia, Jin
Abstract:: Image segmentation continues to be a fundamental problem in computer vision and image understanding. In this thesis, we present a Bayesian network that we use for object boundary detection in which the MPE (most probable explanation) before any evidence can produce multiple non-overlapping, non-self-intersecting closed contours and the MPE with...
Resource Type:: Masters Thesis

An efficient switched capacitor buck-boost voltage regulator using delta-sigma control loop

O Criador:: Rao, Arun
Abstract:: Voltage converters or charge pumps find their use in many circuits. They are extensively used in hand held devices as cell phones, pagers, PDA's and laptops. Some of the important issues relating to design of voltage regulators for handheld devices are size, efficiency and noise. Another important factor to be...
Resource Type:: Masters Thesis

Development of a mobile process to extract phosphorus from livestock wastes as a valuable fertilizer

O Criador:: Hoilman, Gene
Abstract:: Environmental and regulatory concerns are causing confined animal feeding operations (CAFO's) to account for phosphorous content when applying wastewater to agricultural fields for disposal. In most cases this requires more land to spread the waste onto so that the phosphorous needs of the crop are not exceeded. A mobile process...
Resource Type:: Masters Thesis

Calibrating the highway safety manual predictive methods for Oregon rural state highways

O Criador:: Xie, Fei
Abstract:: The first edition of the Highway Safety Manual (HSM) provides a quantitative approach to predict the safety of transportation facilities based on the recently developed scientific methods. This approach, known as the predictive method, was developed for several states in the United States. Due to differences in driver population, weather...
Resource Type:: Masters Thesis

Modeling and dynamics analysis of P2P networks based on evolutionary games

O Criador:: Cho, Seungyun
Abstract:: Since free riders in P2P network reduce the system's performance, how to maintain and encourage the nodes' cooperation is an important aspect of P2P related research. In this thesis, a P2P system is modeled based on two games: stag hunt game and snowdrift game. To relate the model to the...
Resource Type:: Masters Thesis

Development of a dose conversion factor from uptakes of Po-210 through smoking using a modified ICRP 30 lung model

O Criador:: Hout, Jason D.
Abstract:: A thesis presented on the determination of factors related to deposition, clearance, and dosimetry of the ICRP 30 lung model as related to smoking. Variations in calculations used to determine radiation doses leave a need to determine a standard method to determine absorbed dose from smoking. Standard parameters are used...
Resource Type:: Masters Thesis

Mechanical design under changing customer requirements case study : BugID

O Criador:: Fagan, Chris R.
Abstract:: Customer requirements and engineering specifications will influence the direction of the design in any product, so it is crucial to make the requirements as stable as possible so quality designs can be produced on time within a budget. It would be optimal for requirements and specifications to remain constant but...
Resource Type:: Masters Thesis

Ensemble Monte-Carlo planning : an empirical study

O Criador:: Lewis, Paul
Abstract:: Monte-Carlo planning algorithms such as UCT make decisions at each step by intelligently expanding a single search tree given the available time and then selecting the best root action. Recent work has provided evidence that it can be advantageous to instead construct an ensemble of search trees and make a...
Resource Type:: Masters Thesis

Learning multiple non-redundant codebooks with word clustering for document classification

O Criador:: Surve, Akshat Sudhakar
Abstract:: The problem of document classification has been widely studied in machine learning and data mining. In document classification, most of the popular algorithms are based on the bag-of-words representation. Due to the high dimensionality of the bag-of-words representation, significant research has been conducted to reduce the dimensionality via different approaches....
Resource Type:: Masters Thesis

Towards reliable and survivable ocean wave energy converters

O Criador:: Brown, Adam C.
Abstract:: Ocean wave energy is a new and developing field of renewable energy with great potential. The energy contained in one meter of an average wave off the coast of Newport Oregon could supply dozens of homes with electricity. However, ocean waves are usually quite irregular which leads to large bursts...
Resource Type:: Masters Thesis

UCT for tactical assault battles in real-time strategy games

O Criador:: Balla, Radha-Krishna
Abstract:: We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics...
Resource Type:: Masters Thesis

Interactive fault localization techniques to empower the debugging efforts of end-user programmers

O Criador:: Ruthruff, Joseph Ronald
Abstract:: End users develop more software than any other group of programmers, using software authoring devices such as e-mail filtering editors, by-demonstration macro builders, and spreadsheet environments. Despite this, there has been only a little research on finding ways to help these programmers with the dependability of the software they create....
Resource Type:: Masters Thesis

Learning MDP action models via discrete mixture trees

O Criador:: Wynkoop, Michael S.
Abstract:: This thesis addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree models of the conditional probability distributions of the DBNs. Existing algorithms presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise....
Resource Type:: Masters Thesis

Scale effects on reinforced concrete beams strengthened for shear with discrete externally bonded carbon fiber-reinforced polymer U-wraps

O Criador:: Dawson, Matthew Ryan
Abstract:: Current ACI design provisions for shear in reinforced concrete (RC) beams strengthened with externally bonded carbon fiber-reinforced polymer (CFRP) U-wraps may not adequately account for the effect of scale. This paper describes tests of 6 geometrically scaled beams to identify possible scale effects of such beams. Results indicated that effective...
Resource Type:: Masters Thesis

A SAT-based planning framework for optimizing resource production

O Criador:: Ventura, Christopher
Abstract:: Domain-independent automated planning is concerned with computing a sequence of actions that can transform an initial state into a desired goal state. Resource production domains form an interesting class of such problems, in that they typically require reasoning about concurrent durative-actions with continuous effects while minimizing some cost function. Although...
Resource Type:: Masters Thesis

Protein secondary structure prediction using conditional random fields and profiles

O Criador:: Shen, Rongkun
Abstract:: Protein secondary structure prediction plays a pivotal role in predicting protein folding in three-dimensions. Its task is to assign each residue one of the three secondary structure classes helix, strand, or random coil. This is an instance of the problem of sequential supervised learning in machine learning. This thesis describes...
Resource Type:: Masters Thesis

Busca

Resultados da Busca

Filtre sua busca