Physical Sciences and Mathematics Commons^™

Tools For Tutoring Theoretical Computer Science Topics, Mark Mccartin-Lim

Doctoral Dissertations

This thesis introduces COMPLEXITY TUTOR, a tutoring system to assist in learning abstract proof-based topics, which has been specifically targeted towards the population of computer science students studying theoretical computer science. Existing literature has shown tremendous educational benefits produced by active learning techniques, student-centered pedagogy, gamification and intelligent tutoring systems. However, previously, there had been almost no research on adapting these ideas to the domain of theoretical computer science. As a population, computer science students receive immediate feedback from compilers and debuggers, but receive no similar level of guidance for theoretical coursework. One hypothesis of this thesis is that immediate …

Neural Models For Information Retrieval Without Labeled Data, Hamed Zamani

Doctoral Dissertations

Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks. Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval. In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or \emph{weakly supervised} solutions for training the models. The proposed learning solutions do not require labeled training data. Instead, …

Response Retrieval In Information-Seeking Conversations, Liu Yang

Doctoral Dissertations

The increasing popularity of mobile Internet has led to several crucial changes in the way that people use search engines compared with traditional Web search on desktops. On one hand, there is limited output bandwidth with the small screen sizes of most mobile devices. Mobile Internet users prefer direct answers on the search engine result page (SERP). On the other hand, voice-based / text-based conversational interfaces are becoming increasing popular as shown in the wide adoption of intelligent assistant services and devices such as Amazon Echo, Microsoft Cortana and Google Assistant around the world. These important changes have triggered several …

Extracting And Representing Entities, Types, And Relations, Patrick Verga

Doctoral Dissertations

Making complex decisions in areas like science, government policy, finance, and clinical treatments all require integrating and reasoning over disparate data sources. While some decisions can be made from a single source of information, others require considering multiple pieces of evidence and how they relate to one another. Knowledge graphs (KGs) provide a natural approach for addressing this type of problem: they can serve as long-term stores of abstracted knowledge organized around concepts and their relationships, and can be populated from heterogeneous sources including databases and text. KGs can facilitate higher level reasoning, influence the interpretation of new data, and …

Efficient Self-Supervised Deep Sensorimotor Learning In Robotics, Takeshi Takahashi

Doctoral Dissertations

Deep learning has been successful in a variety of applications, such as object recognition, video games, and machine translation. Deep neural networks can automatically learn important features given large training datasets. However, the success of deep learning in robotic systems in the real world is still limited mainly because obtaining large datasets and labeling are costly. As a result, much of the successful work in deep learning has been limited to domains where large datasets are readily available or easily collected. To address this issue, I propose a framework for acquiring re-usable skills efficiently combining intrinsic motivation and the control …

Machine Learning Models For Efficient And Robust Natural Language Processing, Emma Strubell

Doctoral Dissertations

Natural language processing (NLP) has come of age. For example, semantic role labeling (SRL), which automatically annotates sentences with a labeled graph representing who did what to whom, has in the past ten years seen nearly 40% reduction in error, bringing it to useful accuracy. As a result, a myriad of practitioners now want to deploy NLP systems on billions of documents across many domains. However, state-of-the-art NLP systems are typically not optimized for cross-domain robustness nor computational efficiency. In this dissertation I develop machine learning methods to facilitate fast and robust inference across many common NLP tasks. First, …

Characterization Of The Anomalous Ph Of Aqueous Nanoemulsions, Kieran P. Ramos

Doctoral Dissertations

Aqueous water-in-oil nanoemulsions have emerged as a versatile tool for use in microfluidics, drug delivery, single-molecule measurements, and other research. Nanoemulsions are often prepared with perfluorocarbons which are remarkably biocompatbile due to their stability, low surface tension, lipophobicity, and hydrophobicity. Therefore it is often assumed that droplet contents are unperturbed by the perfluorinated surface. However, in microemulsions, which are similar to nanoemulsions, it is known that either the pH of the aqueous phase or the ionization constants of encapsulated molecules are different from bulk solution. There is also recent evidence of low pH in perfluorinated aqueous nanoemulsions. The current underlying …

Software-Defined Infrastructure For Iot-Based Energy Systems, Stephen Lee

Doctoral Dissertations

Internet of Things (IoT) devices are becoming an essential part of our everyday lives. These physical devices are connected to the internet and can measure or control the environment around us. Further, IoT devices are increasingly being used to monitor buildings, farms, health, and transportation. As these connected devices become more pervasive, these devices will generate vast amounts of data that can be used to gain insights and build intelligence into the system. At the same time, large-scale deployment of these devices will raise new challenges in efficiently managing and controlling them. In this thesis, I argue that the IoT …

Energy-Aware Algorithms For Greening Internet-Scale Distributed Systems Using Renewables, Vani Gupta

Doctoral Dissertations

Internet-scale Distributed Systems (IDSs) are large distributed systems that are comprised of hundreds of thousands of servers located in hundreds of data centers around the world. A canonical example of an IDS is a content delivery network (CDN) that delivers content to users from a large global deployment of servers around the world. IDSs consume large amounts of energy and their energy requirements are projected to increase significantly in the future. With carbon emissions from data centers increasing every year, use of renewables to power data centers is critical for the sustainability of data centers and for the environment. In …

Function And Dissipation In Finite State Automata - From Computing To Intelligence And Back, Natesh Ganesh

Doctoral Dissertations

Society has benefited from the technological revolution and the tremendous growth in computing powered by Moore's law. However, we are fast approaching the ultimate physical limits in terms of both device sizes and the associated energy dissipation. It is important to characterize these limits in a physically grounded and implementation-agnostic manner, in order to capture the fundamental energy dissipation costs associated with performing computing operations with classical information in nano-scale quantum systems. It is also necessary to identify and understand the effect of quantum in-distinguishability, noise, and device variability on these dissipation limits. Identifying these parameters is crucial to designing …

Game-Assisted Rehabilitation For Post-Stroke Survivors, Hee-Tae Jung

Doctoral Dissertations

Stroke is a leading cause of permanent impairments among its survivors. Although patients need to go through intensive, longitudinal rehabilitation to regain function before the stroke, patients show poor engagement and adherence to rehabilitation therapies which hampers their recovery. As a means to enhance stroke survivors' motivation, engagement, and adherence to intensive and longitudinal rehabilitation, the use of games in stroke rehabilitation has received attention from research and clinical communities. In order to realize this, it is important to take a holistic, end-to-end research approach that encompasses 1) the development of game technologies that are not only entertaining but also …

Neural Generative Models And Representation Learning For Information Retrieval, Qingyao Ai

Doctoral Dissertations

Information Retrieval (IR) concerns about the structure, analysis, organization, storage, and retrieval of information. Among different retrieval models proposed in the past decades, generative retrieval models, especially those under the statistical probabilistic framework, are one of the most popular techniques that have been widely applied to Information Retrieval problems. While they are famous for their well-grounded theory and good empirical performance in text retrieval, their applications in IR are often limited by their complexity and low extendability in the modeling of high-dimensional information. Recently, advances in deep learning techniques provide new opportunities for representation learning and generative models for information …

Adaptive Feature Engineering Modeling For Ultrasound Image Classification For Decision Support, Hatwib Mugasa

Doctoral Dissertations

Ultrasonography is considered a relatively safe option for the diagnosis of benign and malignant cancer lesions due to the low-energy sound waves used. However, the visual interpretation of the ultrasound images is time-consuming and usually has high false alerts due to speckle noise. Improved methods of collection image-based data have been proposed to reduce noise in the images; however, this has proved not to solve the problem due to the complex nature of images and the exponential growth of biomedical datasets. Secondly, the target class in real-world biomedical datasets, that is the focus of interest of a biopsy, is usually …

Feature Space Modeling For Accurate And Efficient Learning From Non-Stationary Data, Ayesha Akter

Doctoral Dissertations

A non-stationary dataset is one whose statistical properties such as the mean, variance, correlation, probability distribution, etc. change over a specific interval of time. On the contrary, a stationary dataset is one whose statistical properties remain constant over time. Apart from the volatile statistical properties, non-stationary data poses other challenges such as time and memory management due to the limitation of computational resources mostly caused by the recent advancements in data collection technologies which generate a variety of data at an alarming pace and volume. Additionally, when the collected data is complex, managing data complexity, emerging from its dimensionality and …

Allocative Poisson Factorization For Computational Social Science, Aaron Schein

Doctoral Dissertations

Social science data often comes in the form of high-dimensional discrete data such as categorical survey responses, social interaction records, or text. These data sets exhibit high degrees of sparsity, missingness, overdispersion, and burstiness, all of which present challenges to traditional statistical modeling techniques. The framework of Poisson factorization (PF) has emerged in recent years as a natural way to model high-dimensional discrete data sets. This framework assumes that each observed count in a data set is a Poisson random variable $y ~ Pois(\mu)$ whose rate parameter $\mu$ is a function of shared model parameters. This thesis examines a specific …

Probabilistic Models For Identifying And Explaining Controversy, Myungha Jang

Doctoral Dissertations

Navigating controversial topics on the Web encourages social awareness, supports civil discourse, and promotes critical literacy. While search of controversial topics particularly requires users to use their critical literacy skills on the content, educating people to be more critical readers is known to be a complex and long-term process. Therefore, we are in need of search engines that are equipped with techniques to help users to understand controversial topics by identifying them and explaining why they are controversial. A few approaches for identifying controversy have worked reasonably well in practice, but they are narrow in scope and exhibit limited performance. …

Abstractions In Reasoning For Long-Term Autonomy, Kyle Hollins Wray

Doctoral Dissertations

The path to building adaptive, robust, intelligent agents has led researchers to develop a suite of powerful models and algorithms for agents with a single objective. However, in recent years, attempts to use this monolithic approach to solve an ever-expanding set of complex real-world problems, which increasingly include long-term autonomous deployments, have illuminated challenges in its ability to scale. Consequently, a fragmented collection of hierarchical and multi-objective models were developed. This trend continues into the algorithms as well, as each approximates an optimal solution in a different manner for scalability. These models and algorithms represent an attempt to solve pieces …

Data-Driven Approach To Image Classification, Venkatesh Narasimhamurthy

Doctoral Dissertations

Image classification has been a core topic in the computer vision community. Its recent success with convolutional neural network (CNN) algorithm has led to various real world applications such as large scale management of photos/videos on cloud/social-media, image based search for online retailers, self-driving cars, building robots and healthcare. Image classification can be broadly categorized into binary, multi-class and multi-label classification problems. Binary classification involves assigning one of the two class labels to an instance. In multi-class classification problem, an instance should be categorized into one of more than two classes. Multi-label classification is a generalized version of the multi-class …

Massive Graph Analysis In The Data Stream Model, Sofya Vorotnikova

Doctoral Dissertations

Graphs have become an abstraction of choice in modeling highly-structured data. The need to compute graph-theoretic properties of datasets arises in many applications that involve entities and pairwise relations between them. However, in practice the datasets in question can be too large to be stored in main memory, distributed across many machines, or changing over time. Moreover, in an increasing number of applications the algorithm has to make real time decisions as the data arrives, which puts further limitations on the time and space that can realistically be used. These characteristics render classical algorithmic approaches obsolete and necessitate the development …

Poetry: Identification, Entity Recognition, And Retrieval, John J. Foley Iv

Doctoral Dissertations

Modern advances in natural language processing (NLP) and information retrieval (IR) provide for the ability to automatically analyze, categorize, process and search textual resources. However, generalizing these approaches remains an open problem: models that appear to understand certain types of data must be re-trained on other domains. Often, models make assumptions about the length, structure, discourse model and vocabulary used by a particular corpus. Trained models can often become biased toward an original dataset, learning that – for example – all capitalized words are names of people or that short documents are more relevant than longer documents. As a result, …

From Optimization To Equilibration: Understanding An Emerging Paradigm In Artificial Intelligence And Machine Learning, Ian Gemp

Doctoral Dissertations

Many existing machine learning (ML) algorithms cannot be viewed as gradient descent on some single objective. The solution trajectories taken by these algorithms naturally exhibit rotation, sometimes forming cycles, a behavior that is not expected with (full-batch) gradient descent. However, these algorithms can be viewed more generally as solving for the equilibrium of a game with possibly multiple competing objectives. Moreover, some recent ML models, specifically generative adversarial networks (GANs) and its variants, are now explicitly formulated as equilibrium problems. Equilibrium problems present challenges beyond those encountered in optimization such as limit-cycles and chaotic attractors and are able to abstract …

Hierarchical Belief Spaces For Autonomous Mobile Manipulation, Michael W. Lanighan

Doctoral Dissertations

Autonomy in robot systems is a valuable attribute that remains an elusive goal. Noisy sensors, stochastic actions, and variation in unstructured environments all lead to unavoidable errors that can be inconsequential or catastrophic depending on the circumstances. Developing techniques capable of mitigating uncertainty at runtime has, therefore, been a significant and challenging focus of the robotics community. The primary contribution of this dissertation is the introduction of a new hierarchical belief space planning architecture to manage uncertainty and solve tasks using a uniform framework. Such an approach provides a means of creating autonomous systems that focus on salient subsets of …

Efficient Probabilistic Reasoning Using Partial State-Space Exploration, Luis Pineda

Doctoral Dissertations

Planning, namely the ability of an autonomous agent to make decisions leading towards a certain goal, is one of the fundamental components of intelligent behavior. In the face of uncertainty, this problem is typically modeled as a Markov Decision Process (MDP). The MDP framework is highly expressive, and has been used in a variety of applications, such as mobile robots, flow assignment in heterogeneous networks, optimizing software in mobile phones, and aircraft collision avoidance. However, its wide adoption in real-world scenarios is still impaired by the complexity of solving large MDPs. Developing effective ways to tackle this complexity barrier is …

Learning With Aggregate Data, Tao Sun

Doctoral Dissertations

Various real-world applications involve directly dealing with aggregate data. In this work, we study Learning with Aggregate Data from several perspectives and try to address their combinatorial challenges. At first, we study the problem of learning in Collective Graphical Models (CGMs), where only noisy aggregate observations are available. Inference in CGMs is NP- hard and we proposed an approximate inference algorithm. By solving the inference problems, we are empowered to build large-scale bird migration models, and models for human mobility under the differential privacy setting. Secondly, we consider problems given bags of instances and bag-level aggregate supervisions. Specifically, we study …

Machine Learning Methods For Personalized Health Monitoring Using Wearable Sensors, Annamalai Natarajan

Doctoral Dissertations

Mobile health is an emerging field that allows for real-time monitoring of individuals between routine clinical visits. Among others it makes it possible to remotely gather health signals, track disease progression and provide just-in-time interventions. Consumer grade wearable sensors can remotely gather health signals and other time series data. While wearable sensors can be readily deployed on individuals, there are significant challenges in converting raw sensor data into actionable insights. In this dissertation, we develop machine learning methods and models for personalized health monitoring using wearables. Specifically, we address three challenges that arise in these settings. First, data gathered from …

Scalable Data-Driven Modeling And Analytics For Smart Buildings, Srinivasan Iyengar

Doctoral Dissertations

Buildings account for over 40% of the energy and 75% of the electricity usage. Thus, by reducing our energy footprint in buildings, we can improve our overall energysustainability. Further, the proliferation of networked sensors and IoT devices in recent years have enabled monitoring of buildings to provide data at various granularity. For example, smart plugs monitor appliance level usage inside the house, while solar meters monitor residential rooftop solar installations. Furthermore, smart meters record energy usage at a grid-scale. In this thesis, I argue that data-driven modeling applied to the IoT data from a smart building, at varying granularity, in …

Applications Of Machine Learning In Nuclear Imaging And Radiation Detection, Shaikat Mahmood Galib

Doctoral Dissertations

"The main focus of this work is to use machine learning and data mining techniques to address some challenging problems that arise from nuclear data. Specifically, two problem areas are discussed: nuclear imaging and radiation detection. The techniques to approach these problems are primarily based on a variant of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN), which is one of the most popular forms of 'deep learning' technique.

The first problem is about interpreting and analyzing 3D medical radiation images automatically. A method is developed to identify and quantify deformable image registration (DIR) errors from lung CT scans …

Deep Neural Network Learning-Based Classifier Design For Big-Data Analytics, Krishnan Raghavan

Doctoral Dissertations

"In this digital age, big-data sets are commonly found in the field of healthcare, manufacturing and others where sustainable analysis is necessary to create useful information. Big-data sets are often characterized by high-dimensionality and massive sample size. High dimensionality refers to the presence of unwanted dimensions in the data where challenges such as noise, spurious correlation and incidental endogeneity are observed. Massive sample size, on the other hand, introduces the problem of heterogeneity because complex and unstructured data types must analyzed. To mitigate the impact of these challenges while considering the application of classification, a two step analysis approach is …

Volumetric Error Compensation For Industrial Robots And Machine Tools, Le Ma

Doctoral Dissertations

“A more efficient and increasingly popular volumetric error compensation method for machine tools is to compute compensation tables in axis space with tool tip volumetric measurements. However, machine tools have high-order geometric errors and some workspace is not reachable by measurement devices, the compensation method suffers a curve-fitting challenge, overfitting measurements in measured space and losing accuracy around and out of the measured space. Paper I presents a novel method that aims to uniformly interpolate and extrapolate the compensation tables throughout the entire workspace. By using a uniform constraint to bound the tool tip error slopes, an optimal model with …

Structure And Topology Of Transcriptional Regulatory Networks And Their Applications In Bio-Inspired Networking, Satyaki Roy

Doctoral Dissertations

"Biological networks carry out vital functions necessary for sustenance despite environmental adversities. Transcriptional Regulatory Network (TRN) is one such biological network that is formed due to the interaction between proteins, called Transcription Factors (TFs), and segments of DNA, called genes. TRNs are known to exhibit functional robustness in the face of perturbation or mutation: a property that is proven to be a result of its underlying network topology. In this thesis, we first propose a three-tier topological characterization of TRN to analyze the interplay between the significant graph-theoretic properties of TRNs such as scale-free out-degree distribution, low graph density, small …