Search Constraints

Start Over
Filtering by: Creator Reitz, Stuart R. Remove constraint Creator: Reitz, Stuart R. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Code generation in the Oregon speedcode universe

    Creator:
    Armstrong, James R. (James Russel)
    Abstract:
    The purpose of this project was to create a code generating software tool, which is one section of the Oregon SpeedCode Universe. The Code Generator automatically generates compilable source code to form working Macintosh applications. This source code provides a prototype for the actual final application. This is done with...
    Resource Type:
    Masters Thesis
    Full Text:
    ABSTRACT OF THE THESIS OF James R. Armstrong for the degree of Master of Science in Computer Science

  • Mental Models of Mere Mortals with Explanations of Reinforcement Learning

    Creator:
    Anderson, Andrew A.
    Abstract:
    How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated...
    Resource Type:
    Masters Thesis
    Full Text:
    vector ~R(s, a), which gives the reward for each type. The total scalar reward is the sum across types

  • Distributed OpenCL : a platform for distributed, heterogeneous computing for domain scientists

    Creator:
    Dillon, William H.
    Abstract:
    It is possible to purchase, for as little as $10,000, a cluster of computers with the capability to rival the supercomputers of only a few years ago. Now, users that have little to no experience developing distributed applications or managing a cluster are in a position to do so. To...
    Resource Type:
    Dissertation
    Full Text:
    of easy-to-use numerical modeling tools such as Matlab, R and Mathematica, it has become easier for

  • Machine Learning for Precision Medicine: Application to Cancer Chemotherapy Response Prediction and Wound Healing Status Assessment

    Creator:
    Wei, Qi
    Abstract:
    Ph.D. candidate Qi Wei's thesis consists of two projects: Chemotherapy Project: a study based on the research paper "Predicting chemotherapy response of various cancer types using a variational auto-encoder approach" submitted to the bioRxiv preprint archive and accepted by the BMC bioinformatics; and Wound Monitor Project: implementing and assessing analytics...
    Resource Type:
    Dissertation

  • Shrunken learning rates do not improve AdaBoost on benchmark datasets

    Creator:
    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
    Full Text:
    problems that fit into this framework depending on the values of y. If y E R, the problem is called

  • Comparing Chemical Kinetic Model Reduction Techniques Using pyMARS

    Creator:
    Mestas, Phillip O., III
    Abstract:
    Accurately modeling the chemistry of conventional and alternative liquid transportation fuels in combustion technology is vital to predicting important quantities such as the burning rate, heat release, and pollutant emissions. However, incorporating detailed chemical kinetic models into reactive-flow simulations poses a significant challenge due to the associated high computational expense...
    Resource Type:
    Honors College Thesis
    Full Text:
    . doi: 10.1016/j.combustflame.2009.12.022. [5] Y. Ra and R. D. Reitz. “A reduced chemical kinetic model

  • Exploring and Implementing the "Monitoring of a Multi-stage Manufacturing Process" using Dynamic Bayesian Networks

    Creator:
    Jearanaitanakij, Kietikul (Lee)
    Abstract:
    Hewlett-Packard (HP) is one of the world's largest computer companies and the foremost producer of test and measurement instruments. In Corvallis, Oregon, HP manufactures several precision products on high speed, automated assembly lines. The alignment process of a cap to a base part is one of the essential processes in...
    Resource Type:
    Capstone Project
    Full Text:
    : 10 r ) • For each time slice, we treat all the state variables (STl, ST2, and ST3) as a

  • On Avoiding Power-Seeking by Artificial Intelligence

    Creator:
    Turner, Alexander M.
    Abstract:
    We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether—absent a full solution to this AI alignment problem—we can build smart {\ai} agents which have limited impact on the world, and which do not autonomously seek power. In this thesis, I...
    Resource Type:
    Dissertation
    Full Text:
    In this work, we consider a standard Markov decision process (mdp) ⟨S,A, T,R, γ⟩ with state space S

  • Multi-criteria average reward reinforcement learning

    Creator:
    Natarajan, Sriraam
    Abstract:
    Reinforcement learning (RL) is the study of systems that learn from interaction with their environment. The current framework of Reinforcement Learning is based on receiving scalar rewards, which the agent aims to maximize. But in many real world situations, tradeoffs must be made among multiple objectives. This necessitates the use...
    Resource Type:
    Masters Thesis
    Full Text:
    Learning - R Learning 12 2.6 Model Based Average Reward Reinforcement Learning H Learning 15 Chapter 3

  • Version Control Systems: An Information Foraging Perspective

    Creator:
    Srinivasa Ragavan, Sruti
    Abstract:
    Software history and version control systems (VCS) are an important source of information for developers. This entails the need for a principled understanding of developers’ information seeking in VCS, both for improving existing tools as well as understanding requirements for new tools. However, it is only recently that researchers have...
    Resource Type:
    Masters Thesis
    Full Text:
    es (n um be re d la be ls) , , c on ne ct ed b y lin ks (r ed a rr ow s

  • Causal Structure Learning from Experiments and Observations

    Creator:
    Sinha, Meghamala
    Abstract:
    In this research, we address the problem of learning a single causal network structure from multiple dataset generated from different experiments. The experiments can be observational or interventional. We assume that each dataset is generated by an unknown causal network altered under different experimental conditions (interventions, manipulation or perturbation). As...
    Resource Type:
    Masters Thesis
    Full Text:
    bnLearn R package [35]. 13 Chapter 5: Comparative Studies 5.1 Biological Signaling Network In this

  • Layered rendering model for human teeth

    Creator:
    Shetty, Sudarshanram
    Abstract:
    This study introduces a layered model for rendering human teeth. Human teeth exhibit complex light interaction due to their layered structure. While the lighting responses of teeth have been studied in the dental industry for the production of realistic looking dentures, to our knowledge this is the first study of...
    Resource Type:
    Masters Thesis
    Full Text:
    ] is φ(x)= Φ 4πD e−σtrr(x) r(x) where: Φ=power of point light source. σtr=Effective transport

  • Incorporating and Learning Behavior Constraints for Sequential Decision Making

    Creator:
    Pinto, Jervis
    Abstract:
    Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
    Resource Type:
    Dissertation
    Full Text:
    current program location `′ is at choice (A′, a′). The last choice is (A, a) with reward r seen in

  • Morality of biometrics

    Creator:
    Tao, Dany
    Abstract:
    "‘Biometrics is at the forefront in our agenda for homeland security,’ declared Asa Hutchinson, the Department of Homeland Security's undersecretary for border and transportation security, at the 2004 Biometric Consortium Conference” [11]. Flashy retinal scanning and voice activated computers were once considered technologies for science fiction movies and novels. Nowadays,...
    Resource Type:
    Honors College Thesis
    Full Text:
    THE THESIS OF Dany R. Tao for the degree of Honors Baccalaureate of Science in Computer Science

  • Facilitating Code Comprehension by Annotations in Canvas-Based IDE

    Creator:
    Adeli, Marjan
    Abstract:
    Developers spend a considerable amount of time comprehending code and building accurate mental models of the code. Understanding the relationships between software features within IDEs is difficult, with information split across different visual hierarchies making navigation cumbersome. Canvas-based IDEs mitigate some of the navigation costs by allowing relevant information to...
    Resource Type:
    Masters Thesis

  • How do Programmers Forage through Variants? Modeling Hierarchical Foraging and Changelogs

    Creator:
    Pandya, Bhargav Chandravadan
    Abstract:
    Complex information environments are often organized as hierarchies. However, computational models of Information Foraging Theory (IFT) have almost entirely ignored this fact. Models and tools for predicting programmer navigations have ignored people’s foraging behavior across hierarchies —called hierarchical foraging. Without modeling hierarchical foraging, our ability to build tools to support...
    Resource Type:
    Masters Thesis
    Full Text:
    r, assign rank = r+(t-1)/2 to all t patch nodes. • Return the rank for the node representing the (k

  • Anomaly Detection and Probabilistic Diagnosis for Automated Data Quality Control

    Creator:
    Zemicheal, Tadesse H.
    Abstract:
    Advances in sensor technology are greatly expanding the range of quantities that can be measured while simultaneously reducing the cost. However, deployed sensors drift out of calibration and fail, so every sensor network requires quality control procedures to promptly detect these failures. To address these problems, we propose a two-level...
    Resource Type:
    Dissertation
    Full Text:
    recalibrate the sensors. Hence, we need to include a variable r(t) that is 1 if a technician has visited the

  • Variations Foraging

    Creator:
    Srinivasa Ragavan, Sruti
    Abstract:
    Information Foraging Theory (IFT) has successfully explained how people seek information in various domains, in turn, informing the design of several tools and information-intensive environments. However, prior research has not explored foraging in the presence of several, very similar variants of the same artifact. Such variants are commonplace in several...
    Resource Type:
    Dissertation
    Full Text:
    ACT-R cognitive architecture [1] with a scent-computation module, thereby building an ACT-Scent

  • Data Flow/Operating System : DF/OS

    Creator:
    England, Laurence E.
    Abstract:
    This paper discusses a new approach to the design of operating systems. We view the jobs or tasks in this system as a number of small independent steps or functions which are sequenced together to produce a desired result. The con­cepts upon which this operating system is based are drawn...
    Resource Type:
    Capstone Project
    Full Text:
    . Of the 26 actions that are listed, 6 actions are the DFM executions while the r emaining 20 actions

  • Revisiting output coding for sequential supervised learning

    Creator:
    Hao, Guohua
    Abstract:
    Markov models are commonly used for joint inference of label sequences. Unfortunately, inference scales quadratically in the number of labels, which is problematic for training methods where inference is repeatedly preformed and is the primary computational bottleneck for large label sets. Recent work has used output coding to address this...
    Resource Type:
    Masters Thesis
    Full Text:
    xit and the predictions of the previous h binary CRFs at sequence positions from t − l to t + r (l

  • Mood-dynamic playlist : interpolating a path of emotions using a KNN algorithm

    Creator:
    Gaur, Shaurya
    Abstract:
    Users curate music playlists based on emotion to focus or relax, so streaming services often create playlists of songs to aid this process. Prior research focuses on generating playlists of a single mood or genre, although a few studies work to construct automatic playlists that transition between the genres of...
    Resource Type:
    Honors College Thesis

  • Generalizing abstractions in form-based visual programming languages : from direct manipulation to static representation

    Creator:
    Yang, Sherry
    Abstract:
    We believe concreteness, direct manipulation and responsiveness in a visual programming language increase its usefulness. However, these characteristics present a challenge in generalizing programs for reuse, especially when concrete examples are used as one way of achieving concreteness. In this thesis, we present a technique to solve this problem by...
    Resource Type:
    Dissertation
    Full Text:
    rixActive Underline Icon teration MOUSE-Exception ReCalcCon aaaaa nt InSuperscript R rrrrr hAll

  • Rare category detection using hierarchical mean shift

    Creator:
    Vatturi, Pavan Kumar
    Abstract:
    Many applications in surveillance, monitoring, scientific discovery, and data cleaning require the identification of anomalies. Although many methods have been developed to identify statistically significant anomalies, a more difficult task is to identify anomalies that are both interesting and statistically significant. Category detection is an emerging area of machine learning...
    Resource Type:
    Masters Thesis
    Full Text:
    the distance between this example and its Kthi4 nearest neighbor; Set r ′ i to be the minimum value

  • Structured gradient boosting

    Creator:
    Parker, Charles (Charles Lincoln)
    Abstract:
    The goal of many machine learning problems can be formalized as the creation of a function that can properly classify an input vector, given a set of examples of that function. While this formalism has produced a number of success stories, there are notable situations in which it fails. One...
    Resource Type:
    Dissertation
    Full Text:
    generally, a vector 8 of real numbers1 of some fixed size d so that X = ℜd. If Y = ℜ, then this is a

  • Analytical Methods for Improving Causal Inference

    Creator:
    Sinha, Meghamala
    Abstract:
    Causal inference is an important analytical tool to bridge the gap between prediction and decision-making. However, learning a causal network solely from data is a challenging task. In this work, various techniques have been explored for a better and improved causal network learning from data. Firstly, the problem of learning...
    Resource Type:
    Dissertation

  • Electra : integrating constraints, condition-based dispatching, and features exclusion into the multiparadigm language Leda

    Creator:
    Zamel, Nabil M.
    Abstract:
    Multiparadigm languages are languages that are designed to support more than one style of programming. Leda is a strongly-typed multiparadigm programming language that supports imperative, functional, object-oriented, and logic programming. The constraint programming paradigm is a declarative style of programming where the programmer is able to state relationships among some...
    Resource Type:
    Dissertation
    Full Text:
    research, Masami Takikawa who taught me a lot about constraints, and Dr. Leine Stuart who has been a

  • Efficient training and feature induction in sequential supervised learning

    Creator:
    Hao, Guohua
    Abstract:
    Sequential supervised learning problems arise in many real applications. This dissertation focuses on two important research directions in sequential supervised learning: efficient training and feature induction. In the direction of efficient training, we study the training of conditional random fields (CRFs), which provide a flexible and powerful model for sequential...
    Resource Type:
    Dissertation

  • The InclusiveMag Method: A Start Towards More Inclusive Software for Diverse Populations

    Creator:
    Mendez, Christopher
    Abstract:
    How can software practitioners assess whether their software supports diverse users? Although there are empirical processes that can be used to find “inclusivity bugs” piecemeal, what is often needed is a systematic inspection method to assess software’s support for diverse populations. To help fill this gap, this thesis introduces InclusiveMag,...
    Resource Type:
    Masters Thesis

  • Bayesian methods for knowledge transfer and policy search in reinforcement learning

    Creator:
    Wilson, Aaron
    Abstract:
    How can an agent generalize its knowledge to new circumstances? To learn effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
    Resource Type:
    Dissertation
    Full Text:
    (Parameter set Ψ). There are N tasks. For each task the agent has made R observations. The class

  • Learning and Improving Policies for Probabilistic Planning Problems

    Creator:
    Issakkimuthu, Murugeswari
    Abstract:
    In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.4 FC-DRP vs S-DRP vs R-DRP Results . . . . . . . . . . . . . . . . . . . . 19 3.1 Game-of-Life

  • Analysis of Bayesian anytime inference algorithms

    Creator:
    Burgess, Scott Alan
    Abstract:
    This dissertation explores and analyzes the performance of several Bayesian anytime inference algorithms for dynamic influence diagrams. These algorithms are compared on the On-Line Maintenance Agent testbed, a software artifact permitting comparison of dynamic reasoning algorithms used by an agent on a variety of simulated maintenance and monitoring tasks. Analysis...
    Resource Type:
    Dissertation

  • Computational Elucidation of the Regulatory SNPs in the Non-Coding Regions of the Human Genome

    Creator:
    Yao, Yao
    Abstract:
    We describe a series of novel computational models, CERENKOV (Computational Elucidation of the REgulatory NonKOding Variome) and its successors CERENKOV2, CERENKOV3, and Convolutional CERENKOV3, for discriminating regulatory single nucleotide polymorphisms (rSNPs) from non-regulatory SNPs within non-coding genetic loci. The CERENKOV models are designed for recognizing rSNPs in the context of...
    Resource Type:
    Dissertation
    Full Text:
    define, for the sets L ⊂ Z+ of numbered loci, S ⊂ Z+ of numbered SNPs, and R ⊂ S of numbered rSNPs. Then

  • Newcomers’ Barriers. . . Is That All? An Analysis of Mentors’ and Newcomers’ Barriers in OSS Projects

    Creator:
    Balali, Sogol
    Abstract:
    Newcomers’ seamless onboarding is important for open collaboration communi- ties, particularly those that leverage outsiders’ contributions to remain sustainable. Nevertheless, previous work shows that OSS newcomers often face several barriers to contribute, which lead them to lose motivation and even give up on contributing. A well-known way to help newcomers...
    Resource Type:
    Masters Thesis

  • Interpretable Machine Learning: Applications in Biology and Genomics

    Creator:
    Danaee, Padideh
    Abstract:
    Machine learning (ML) and deep learning (DL) models impact our daily lives with applications in natural language modeling, image analysis, healthcare, genomics, and bioinformatics. The exponential growth of biological sequence data necessitates accompanying advances in computational methods. Although deep learning is highly effective for detecting and classifying biological sequences, challenges...
    Resource Type:
    Dissertation

  • Exploration of regression models for cancer noncoding mutation recurrence

    Creator:
    Xu, Tanjin
    Abstract:
    An important impact of the genome technology revolution will be the elucidation of mechanisms of cancer pathogenesis, leading to improvements in the diagnosis of cancer and the selection of cancer treatment. Integrated with current well-studied massive knowledge and findings about the role of protein-coding mutations in cancer, demystifying the functional...
    Resource Type:
    Masters Thesis
    Full Text:
    → R. 2. Calculate the adjusted error eti for each instance: (a) let Dt = maxnj=1|yi − ht(xj)| (b

  • Learning affinities of exemplar videos for multi-view action recognition

    Creator:
    Roy, Anirban
    Abstract:
    This thesis addresses a fundamental computer vision problem, that of action recognition. The goal of action recognition is to recognize a class of human actions in a given video. Action recognition has a wide range of applications, including automated surveillance, sports video analysis, internet-based searches etc. The main challenge is...
    Resource Type:
    Masters Thesis

  • A probabilistic model for anomaly detection in remote sensor streams

    Creator:
    Dereszynski, Ethan W.
    Abstract:
    Remote sensors are becoming the standard for observing and recording ecological data in the field. Such sensors can record data at fine temporal resolutions, and they can operate under extreme conditions prohibitive to human access. Unfortunately, sensor data streams exhibit many kinds of errors ranging from corrupt communications to partial...
    Resource Type:
    Masters Thesis

  • Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

    Creator:
    Wang, Xinyao
    Abstract:
    Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
    Resource Type:
    Masters Thesis
    Full Text:
    ou r m o d el . T h e st ac k ed H G ta ke s a fa ce im ag e cr op p ed w it h th e g

  • Learning with Partial Supervision for Clustering and Classification

    Creator:
    Pei, Yuanli
    Abstract:
    In the field of machine learning, clustering and classification are two fundamental tasks. Traditionally, clustering is an unsupervised method, where no supervision about the data is available for learning; classification is a supervised task, where fully-labeled data are collected for training a classifier. In some scenarios, however, we may not...
    Resource Type:
    Dissertation
    Full Text:
    labeled constraints and correctly labeled constraints used in the comparison of Figure 3.9. “R”: relative

  • Interactive visualization of diversity in multivariate data sets unified across fields of study

    Creator:
    Pham, Tuan N. T.
    Abstract:
    The study of the diversity of multivariate objects shares common characteristics across disciplines, including ecology and organizational management. Nevertheless, experts in these two disciplines have adopted somewhat separate diversity concepts and analysis techniques, limiting the ability of potentially sharing and cross comparing these concerns. Moreover, while complex diversity data may...
    Resource Type:
    Dissertation

  • Interactive football playbook

    Creator:
    Neumann, Christoph
    Abstract:
    This thesis presents a domain specific visual language designed to allow coaches to create content that exhibits the complex 2D interactions observed in the game of American football. Coaches can visually program the content by using symbols and drawing primitives similar to those that they currently use to design static...
    Resource Type:
    Masters Thesis

  • Similarity inheritance : a model of inheritance for declarative visual programming languages

    Creator:
    Djang, Rebecca W. (Rebecca Walpole)
    Abstract:
    Declarative visual programming languages (VPLs), including spreadsheets, make up a large portion of both research and commercial VPLs. Spreadsheets in particular enjoy a wide audience, including end users. Unfortunately, spreadsheets and most other declarative VPLs still suffer from some of the problems that have been solved in other languages, such...
    Resource Type:
    Dissertation
    Full Text:
    ) (((a (a 3), 3), +r) .,+yj 8)- e)- ie) (WOW. -+ c+)-+ -+ fi) 13) .1 -. fi) 13) - 13)(. .1 (0. (Y. 13

  • The Past, Present, and Future of American Election Security: A Survey

    Creator:
    Read, Lyell
    Abstract:
    The widespread adoption of computerized systems around the turn of the century as a means of more efficiently conducting elections introduced more issues than these computer systems were intended to address. Though many of these flaws were not considered for years or decades after the introduction of digital election infrastructure,...
    Resource Type:
    Honors College Thesis

  • High-Dimensional Reinforcement Learning with Human Feedback

    Creator:
    Curran, William
    Abstract:
    State-of-the-art personal robots need to perform complex manipulation tasks to be viable in complex scenarios. However, many of these robots, like the PR2, use manipulators with high degrees of freedom. High degrees of freedom are desirable from a functionality standpoint, but make the learning task more difficult by adding a...
    Resource Type:
    Dissertation
    Full Text:
    reward function, R: J(π) = ∑ s,a µπ(s)π(s, a)R(s, a) (2.1) where µπ(s) is the probability distribution

  • Variational Satisfiability Solving

    Creator:
    Young, Jeffrey M.
    Abstract:
    Over the last two decades, satisfiability and satisfiability-modulo theory (SAT/SMT) solvers have grown powerful enough to be general purpose reasoning engines throughout software engineering and computer science. However, most practical use cases of SAT/SMT solvers require not just solving a single SAT/SMT problem, but solving sets of related SAT/SMT problems....
    Resource Type:
    Dissertation
    Full Text:
    ∧ c ∧ e q = a ∧ (b ∨ ¬i) ∧ c ∧ (g → c) r = z ↔ (a ∧ b ∧ c ∧ e) 2By the standard, this is a well

  • Effective decision-theoretic assistance through relational hierarchical models

    Creator:
    Natarajan, Sriraam
    Abstract:
    Building intelligent computer assistants has been a long-cherished goal of AI. Many intelligent assistant systems were built and fine-tuned to specific application domains. In this work, we develop a general model of assistance that combines three powerful ideas: decision theory, hierarchical task models and probabilistic relational languages. We use the...
    Resource Type:
    Dissertation

  • Probabilistic models for quality control in environmental sensor networks

    Creator:
    Dereszynski, Ethan W.
    Abstract:
    Networks of distributed, remote sensors are providing ecological scientists with a view of our environment that is unprecedented in detail. However, these networks are subject to harsh conditions, which lead to malfunctions in individual sensors and failures in network communications. This behavior manifests as corrupt or missing measurements in the...
    Resource Type:
    Dissertation

  • Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties

    Creator:
    Dodge, Jonathan E.
    Abstract:
    Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools (e.g., a professional auditor, a developer, and an end user all have different needs). We posit that it is possible to provide...
    Resource Type:
    Dissertation

  • Probabilistic computation in stochastic pulse neuromime networks

    Creator:
    Hangartner, Ricky Dale
    Resource Type:
    Dissertation
    Full Text:
    allowable approximation error and the maximum of the second derivative over [to, t1]: R = max d2 to

  • How does AAR/AI Support Problem Solvers with Diverse Behaviors and Cognitive Styles?

    Creator:
    Dikkala, Rupika
    Abstract:
    "What’s wrong with this AI?" Explainable AI (XAI) researchers are moving beyond explaining an AI’s actions, to helping users detect an AI’s failures. However this detection may not be enough—for actionability, we often need to pinpoint which part failed. We investigate how AAR/AI, a structured assessment process, supports users with...
    Resource Type:
    Masters Thesis

  • Design and Application of Variational Representations

    Creator:
    Smeltzer, Karl J.
    Abstract:
    Variability is an important and widely studied topic across domains such as version control, software product lines, and metaprogramming. This dissertation presents an investigation into the process of systematically adding variability to data structures and programs, leading to guidelines for variational data structures and implications for programs that create, manipulate,...
    Resource Type:
    Dissertation

  • Semantic embodied navigation : developing agents that navigate from language and vision

    Creator:
    Krantz, Jacob
    Abstract:
    Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
    Resource Type:
    Dissertation

  • Assessing and Finding Faults in AI: Two Empirical Studies

    Creator:
    Khanna, Roli
    Abstract:
    With the advent of Artificial Intelligence (AI) in every sphere of life in today's day and age, it has become increasingly important for non-AI experts to be able to comprehend the underlying logic of how AI systems work, assess them and find faults in these systems, particularly when they are...
    Resource Type:
    Masters Thesis
    Full Text:
    , Andrew Anderson, Rupika Dikkala, Jed Irvine, Zeyad Shureih, Kin-Ho Lam, Caleb R. Matthews, Minsuk Kahng

  • New learning modes for sequential decision making

    Creator:
    Judah, Kshitij
    Abstract:
    This thesis considers the problem in which a teacher is interested in teaching action policies to computer agents for sequential decision making. The vast majority of policy learning algorithms o er teachers little flexibility in how policies are taught. In particular, one of two learning modes is typically considered: 1)...
    Resource Type:
    Dissertation
    Full Text:
    , r t i) } , t = 1 . . . Li and s t i, a t i, and rti are the state, action and reward at time t

  • Elucidating Computational Narratives to Facilitate Code Comprehension

    Creator:
    Chattopadhyay, Souti
    Abstract:
    Programming is integrated across the workflow of multiple domains where end-user programmers, those who need to program as a means to an end, regularly need to code. In the modern setting of collaborative development, end-user programmers have to interpret the intentions behind existing code to contribute and build solutions to...
    Resource Type:
    Dissertation
    Full Text:
    LANGUAGES FP1 Data Scientist Advertising 5 Jupyter, RStudio Python, R FP2 Data Scientist Cloud Computing

  • Toward computer vision for understanding American football in video

    Creator:
    Hess, Robin W.
    Abstract:
    In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...
    Resource Type:
    Dissertation

  • Supporting merge comprehension when resolving merge conflicts

    Creator:
    Nelson, Nicholas
    Abstract:
    Distributed version control allows developers to manage software evolution among distributed development teams. But it does not eliminate all consistency and concurrency issues, and instead introduces additional complexity when merging code. And resolving merge conflicts is nontrivial when automated merging fails. In such cases, developers are forced to inspect the...
    Resource Type:
    Dissertation

  • Empowering End Users to Mitigate Privacy and Security Risks in Smart-Home Trigger-Action Apps

    Creator:
    Saeidi, Mahsa
    Abstract:
    Many home users nowadays use various smart devices to improve the efficiency and convenience of their home environments. Trigger-action platforms such as “If-This-Then-That” (IFTTT) enable end users to connect different smart devices and services using simple apps to control these devices and automate the tasks (e.g., if the camera detects...
    Resource Type:
    Dissertation
    Full Text:
    results using Random Forest (R#: The num- ber of rules, V: Violating, NV: Non-Violating

  • Monte-Carlo planning for probabilistic domains

    Creator:
    Bjarnason, Ronald V.
    Abstract:
    This thesis presents a progression of novel planning algorithms that culminates in a new family of diverse Monte-Carlo methods for probabilistic planning domains. We provide a proof for performance guarantees and analyze how these algorithms can resolve some of the shortcomings of traditional probabilistic planning methods. The direct policy search...
    Resource Type:
    Dissertation
    Full Text:
    transition function and a reward, commonly represented as a 4-tuple (S,A, T ,R). All objects and features of

  • An Investigation of the Effects of Merge Conflicts on Collaborative Software Development

    Creator:
    Brindescu, Caius
    Abstract:
    Merge conflicts have long plagued software development. With larger and more dispersed teams comes greater risk of developers working on the same code at the same time. While merge conflicts are known to be painful, their exact impact on software is still largely unknown. Are merge conflicts an isolated problem,...
    Resource Type:
    Dissertation

  • Multiagent learning for locomotion and coordination in tensegrity robotics

    Creator:
    Iscen, Atil
    Abstract:
    Tensegrity structures are composed of pure compressional elements that are connected via a network of pure tensional elements. The concept of tensegrity promises numerous advantages to the field of robotics. Tensegrity robots are, however, notoriously difficult to control due to their oscillatory nature and nonlinear interaction between the components. Multiagent...
    Resource Type:
    Dissertation

  • An empirical study into learning through experimentation

    Creator:
    Ruff, Ritchey Alvin
    Abstract:
    A key aspect of how we understand the world revolves around an ability to manipulate our surroundings to experiment. From the scientific method through theories of child development, the ability to experiment is deemed critical; however, few studies have been performed to understand the strengths and weaknesses of different experimental...
    Resource Type:
    Dissertation

  • Designing Diversity and Inclusion Processes and Tools for Sustainable Open Source

    Creator:
    Guizani, Mariam
    Abstract:
    Over time, Open Source Software (OSS) has become indispensable in the creation and upkeep of software products, serving as the fundamental building block for widely used solutions in our daily lives, including applications that enable communication, entertainment, and productivity. A sustainable OSS ecosystem is one that attracts and retains a...
    Resource Type:
    Dissertation