Assistive robotics focuses on human-robot systems that provide physical support and assistance to the elderly and people with motor-impairments. While assistive machines, such as the powered wheelchair, can significantly enhance the functional independence of individuals, many users are challenged by their direct operation, the manner in which such systems are...
In the near future, self-driving or driverless vehicles will operate without human control, enabling passengers to use their time in new ways. This opens up avenues for designing new interactions and experiences for individuals or groups traveling in an automobile. For that scenario, automobile manufacturers propose developing bigger and better...
In the Maximum-a-Posteriori (MAP) Inference problem, for any given probability distribution, the goal is to find the point in the support of that distribution with the highest probability. Potts models and Determinantal Point Processes (DPPs) are probabilistic models that were introduced in the context of statistical physics several decades ago....
A core problem in many computer vision applications is visual recognition (including object classification, detection and localization). Recent advances in artificial neural networks (aka ”deep learning”) have significantly pushed forward the state-of-the-art visual recognition performances. However, due to the lack of semantic structure modeling, most current deep learning approaches do...
The Operating System (OS) kernel is a key component of modern computing infrastructure, yet it is prone to numerous vulnerabilities, many of which cause memory corruptions that can be exploited by attackers to perform malicious activities. While various techniques have been introduced to secure the Linux kernel, it still constantly...
Super-resolution (SR) has become one of the most critical problems in image and video processing. In Chapter 2 of this thesis, a detailed review of existing Deep Learning (DL) techniques for addressing the SR task, with an emphasis on how DL and analytical techniques can be combined, is provided. Chapter...
Recent developments in deep learning have led to breakthroughs in rendering novel views from sparse input views of a scene.While the accuracy of these algorithms has improved dramatically, it has come at a huge computational cost.
While developments in graphics hardware have ameliorated some of the computational burdens, deep learning-based...
While there is high demand for university computer science (CS) courses, students often struggle when learning to program. Prior work has identified that student perceptions of their programming ability may contribute to these challenges. For example, studies show that students often perceive that they do not belong, are not capable...
Modeling human language is at the very frontier of machine learning and artificial intelligence. Statistical language models are probabilistic models that assign probabilities to sequences of words. For example, topic models are frequently used text-mining tools to organize a vast set of unstructured documents by exploring their theme structure. More...
We address the problem of efficient maintenance of the answer to a new type of query: Continuous Maximizing Range-Sum (Co-MaxRS) for moving objects trajectories. The traditional static/spatial MaxRS problem finds a location for placing the centroid of a given (axes-parallel) rectangle $R$ so that the sum of the weights of...
Many computing technologies are primarily useful because of the existence of some set of data created by people, intentionally in some cases and unintentionally in others. For instance, technologies like search engines, recommender systems, classifiers, and language models are all dependent on digital records of things people have said, done,...
Wearable-based human activity recognition is well-studied in the machine learning and pervasive computing community. A large corpus of studies focused on using wearable sensors to recognize health-related behaviors that involve high periodicity in the sensed signal, such as sitting, walking, and running. Other activities that occur less frequently throughout the...
As our world is increasingly filled with data visualizations, having the skills to leverage data visualizations is essential for participation in society. Confident engagement with data visualizations is critical for being an educated member of society; however, research has shown that it is difficult for individuals to digest and gain...
Polymer nanocomposites are a class of advanced materials comprised of soft polymer matrix and nano-filler inclusions. While it has been found qualitatively that enhancements of material properties could be achieved by dispersing inorganic nano-particles into organic polymer matrix, the intrinsic governing principles of such composite has not been thoroughly studied...
Connecting structure and function in nanoscale engineered materials and devices relies on the analysis of the fundamental arrangement of matter, frequently under dynamic conditions. The demand to image structures at fundamental length scales has touched inorganic materials, biology, and frequently hybrid hard/soft materials with unique phenomena driven by heterogeneous components....
In this dissertation, we study different machine learning algorithms including probabilistic, sparse and deep learning based models applied to multi-sensory datasets. In many machine learning problems, samples are collected from more than one source or modality. Also, various feature extraction methods can be used to provide more than one set...
The current view in neuroscience holds that the brain, together with its sensory and motor structures and the environment, form a closed-loop system – a sensorimotor loop – in which the brain receives information from the environment and converts it into a motor response while simultaneously making predictions about future...
Data mining is multidisciplinary process involving computer science, artificial intelli- gence, and machine learning. The aim of data mining is discovering knowledge from a vast amount of data. This process consists of a set of stages forming a pipeline. This pipeline process consists of multiple steps: 1) Finding the right...
This thesis studies Bayesian-robustness of algorithm design. The main perspective requires for a single fixed algorithm that its performance is an approximation of the optimal performance when its inputs are independent and identical draws (i.i.d.) from every unknown distribution which is an element of a known, large class of distributions....
Blockchains are an exciting new type of Peer-to-Peer (P2P) distributed systems, which enable parties to transact directly, and maintain the record of said interactions in a distributed manner. A unique feature of blockchains is their ability to maintain a consensus without requiring knowledge on the number of participants, nor their...
Memory management and address translation need significant optimizations in order to not behindrances in the near future. Currently, plenty of work has started to address issues within the
current abstraction of the hardware-software codesign of paging. I argue that a new abstraction
is needed in order to properly address this...
Biological systems comprise diverse collections of cellular and non-cellular components with intricate relationships and dynamic interactions. To gain system-level understanding, we must be able to accurately model these systems, both experimentally and computationally. Agent-based models (ABMs) in particular are a uniquely intuitive, modular, and flexible framework capable of supporting multi-scale,...
The ever growing desire for accurate estimation and efficient learning necessitates the efforts to quantitatively characterize uncertainties for models. In this thesis, four problems pertaining to uncertainty quantification are discussed: A sequential stopping framework of constructing fixed-precision confidence regions is proposed for a class of multivariate simulation problems where variance...
The theory of how humans and machines control and communicate with each other is at the core of the scientific field known as Human-Robot Interaction (HRI). Researchers in this sub-discipline of robotics are therefore particularly interested in developing methods to chuppahreduce the inherent friction in this communication and control channel....
Asymmetric relationships between creators and consumers in peer-produced knowledge repositories produce inequitable knowledge representation--or knowledge gaps. These gaps result in unequal access to information, and downstream technologies that leverage peer-produced data perpetuate these inequities. Effective knowledge gap identification represents a necessary first step towards equitable knowledge representation. However, while prior...
From cyber theft of personal financial information to Advanced Persistent Threat (APT) attacks, nowadays endpoint devices suffer from various intrusions which cause inestimable property and privacy loss. To protect the security on endpoints, endpoint detection and response (EDR) systems have been developed to serve as the powerful solution against those...
Newcomers, or new members to organizations or professions, bring insights that are critical to the advancement of society. Yet newcomers often have low self-efficacy, or low beliefs in their abilities to achieve a task, which can impact performance and retention. Research suggests that self-efficacy can be developed through in-person social...
This dissertation combines perspectives from social networks and teams research to advance understanding of team self-assembly. Across three substantive chapters, I explore team member search behaviors and invitation patterns in contexts where individuals exercise agency to select team members. First, I consider the search for team members in a social...
Clustering is a fundamental task in unsupervised learning, which aims to partition the data set into several clusters. It is widely used for data mining, image segmentation, and natural language processing. One of the most popular clustering methods is centroid-based clustering, including k-medians and k-means clustering. k-medians and k-means clustering...
Responsiveness -- the time it takes for a message recipient to respond to a message -- has long been of interest to scholars in the fields of computer-mediated communication and human-computer interaction. It has been hypothesized that responsiveness is used to signal emotional information, and many empirical studies have demonstrated...
Abstract The work presented in this dissertation addresses three broad areas of video signal processing: video transmission, motion estimation and error concealment. In the first category, focused on the source-side, we present two machine learning models for efficient content-aware resource allocation and packet prioritization for video transmission over shared/constrained, lossy...
Sound is one of the most important mediums to understand the environment around us. Identifying a sound event in prerecorded audio (such as a police siren, a dog bark, or a creaking door in soundscapes) leads to a better understanding of the context where the sound events occurred. To do...
Visual matching is an important and fruitful research topic in computer vision area. Starting from the early face recognition, super-resolution, object tracking to the most recent person re-identification, cross-model retrieval, visual matching plays an important role as the core component in these tasks. The quality of visual matching directly and...
Performing complex reasoning has been a long-standing challenge in artificial intelligence (AI).This thesis describes a class of AI systems designed to reason, extract knowledge, and answer
questions on various domains such as process understanding, elementary science, and math word
problems. Our approach differs from traditional logical reasoning systems since we...
Next generation cellular networks are expected to support a massive data traffic volume and satisfy a vast number of users that have latency-critical quality-of-service expectations. Towards serving this demand, it is envisaged that the interference management problem will be the main bottleneck due to the likeliness of a heavily interfering...
Motivated by real-world problems in various fields, mechanism design governs the design of protocols for strategic agents and has applications both in computer science and economics. Due to the revelation principle – a seminal observation in mechanism design, a vast number of studies in mechanism design focus on revelation mechanisms...
In conventional data federations, a set of data providers each possess an autonomous database and collectively make the union of these databases available for querying by a client from a unified SQL interface. This setting however, provides no guarantees on data privacy or security. With my work, I consider a...
The advent of metamaterials—hierarchical structures that manifest properties beyond those found in nature through geometry rather than material composition—inspired new possibilities and research in many fields. In mechanics, periodic metamaterials exhibit behaviors ranging from unprecedented compressibility to extreme stiffness. Numerous geometric classes of metamaterials with these properties have been discovered,...
This dissertation asks how researchers can create more equitable algorithmic systems. Ultimately, this thesis explores methods and implications of representing subjects of analysis in the design and evaluation of algorithmic systems. I also unpack how algorithmic tools measure and quantify human behavior, giving heed to the potential impacts of these...
Annual age-adjusted breast cancer incidence rates in the United States have been static for decades. More recently, the development of massively parallel, high throughput DNA sequencing has enabled the cataloging of somatic mutations in cancer. Mutations are non-random and occur within sequence motifs. These motifs provide us with evidence to...
In the near future, self-driving or driverless vehicles will operate without human control, enabling passengers to use their time in new ways. This opens up avenues for designing new interactions and experiences for individuals or groups traveling in an automobile. For that scenario, automobile manufacturers propose developing bigger and better...
Computational imaging (CI) is a class of imaging systems that optimize both the opto-electronic hardware and computing software to achieve task-specific improvements. Machine/deep learning models have proven effective in drawing statistical priors from adequate datasets. Yet when designing computational models for CI problems, physics-based models derived from the image formation...
Cardiovascular disease is the leading cause of death in US and non-invasive cardiac imaging has vital importance for early detection and diagnosis of heart disease. Cardiac Magnetic Resonance (CMR) is arguably the most versatile imaging modality and capable of a comprehensive evaluation of heart disease without ionization radiation. Despite the...
Volunteer-based physical crowdsourcing systems connect individuals to make unique contributions to solve local and communal problems and enable new services. A key challenge in enabling such systems is attracting enough willing volunteers who can make useful contributions to achieve desired system goals. While most volunteer-based systems provide volunteers flexibility to...
Algorithmically-driven social platforms present a challenge for self-presentation and identity management by obscuring audiences behind algorithmic mechanisms. Users are increasingly aware of this and actively adapting through folk theorization, but we do not know how users are coping with the constant change endemic to these platforms. We also do not...
In this thesis we study two problems, one in unsupervised learning - k-means clustering and the other in a supervised learning setting with the presence of adversarial perturbations. We do a beyond-worst case style analysis and show that in either case instances that are resilient to adversarial perturbations are also...
The past decade has seen the rapid progress of deep learning, which becomes a game-changing technique in different data-intensive domains, with the availability of large scale data, cost-effective computing hardware and more advanced learning theory and algorithms. Despite of the rapid progress of deep learning methods in daily-life applications, such...
Automated driving has become a very popular topic in the recent years and is becoming more and more of a reality. In this new trend, High Definition (HD) maps play an important role in many ways that will provide a safer and more efficient driving experience, especially in terms of...
In this thesis, we aim to develop efficient algorithms with theoretical guarantees for noisy nonlinear optimization problems, with and without constraints, under various different assumptions. Apart from Chapter 1 which provides relevant backgrounds, the remaining of thesis is divided into four chapters. In Chapter 2, we establish the theoretical convergence...
Commonsense inference is a critical capability of modern artificial intelligence (AI) systems. The machines need commonsense knowledge to perform tasks exactly like human being does. Learning commonsense inference from text has been a long standing challenge in the field of natural language processing due to reporting bias -- people do...