Total: 20
Statistical shape modeling (SSM) is an enabling tool in medical image analysis as it allows for population-based quantitative analysis. The traditional pipeline for landmark-based SSM from images requires painstaking and cost-prohibitive steps. My thesis aims to leverage probabilistic deep learning frameworks to streamline the adoption of SSM in biomedical research and practice. The expected outcomes of this work will be new frameworks for SSM that (1) provide reliable and calibrated uncertainty quantification, (2) are effective given limited or sparsely annotated/incomplete data, and (3) can make predictions from incomplete 4D spatiotemporal data. These efforts will reduce required costs and manual labor for anatomical SSM, helping SSM become a more viable clinical tool and advancing medical practice.
When faced with novel tasks, humans have the ability to form successful strategies, seemingly without much effort. Artificial systems, on the other, hand cannot, at least when the flexibility at which humans perform is considered. For my dissertation, I am using program synthesis as a tool to study the factors that affect strategy choices in intelligent systems. I am evaluating my work through agents that reason through problems from the Abstract Reasoning Corpus and The Block Design Task.
Reinforcement learning methods typically discount future rewards using an exponential scheme to achieve theoretical convergence guarantees. Studies from neuroscience, psychology, and economics suggest that human and animal behavior is better captured by the hyperbolic discounting model. Hyperbolic discounting has recently been studied in deep reinforcement learning and has shown promising results. However, this area of research is seemingly understudied, with most extant and continuing research using the standard exponential discounting formulation. My dissertation examines the effects of non-exponential discounting functions (such as hyperbolic) on an agent's learning and aims to investigate their impact on multi-agent systems and generalization tasks. A key objective of this study is to link the discounting rate to an agent's approximation of the underlying hazard rate of its environment through survival analysis.
We propose the use of game-theoretic solutions and multi- agent Reinforcement Learning in the mechanism design of smart, sustainable mobility services. In particular, we present applications to ridesharing as an example of a cost game.
My dissertation research focuses on sequential decision-making (SDM) in complex environments, and how agents can perform well even when novelty is introduced to those environments. The problem of how agents can respond intelligently to novelty has been a long-standing challenge in AI, and poses unique problems across approaches to SDM. This question has been studied in various formulations, including open-world learning and reasoning, transfer learning, concept drift, and statistical relational learning. Classical and modern approaches in agent design offer tradeoffs in human effort for feature encoding, ease of deployment in new domains, and the development of both provably and empirically reliable policies. I propose a formalism for studying open-world novelty in SDM processes with feature-rich observations. I study the conditions under which causal-relational queries can be estimated from non-novel observations, and empirically examine the effects of open-world novelty on agent behavior.
The main goal of this thesis is to develop efficient non-parametric density estimation methods that can be integrated with deep learning architectures, for instance, convolutional neural networks and transformers. Density estimation methods can be applied to different problems in statistics and machine learning. They may be used to solve tasks such as anomaly detection, generative models, semi-supervised learning, compression, text-to-speech, among others. The present work will mainly focus on the application of the method in anomaly and outlier detection tasks such as medical anomaly detection, fraud detection, video surveillance, time series anomaly detection, industrial damage detection, among others. A recent approach to non-parametric density estimation is neural density estimation. One advantage of these methods is that they can be integrated with deep learning architectures and trained using gradient descent. Most of these methods are based on neural network implementations of normalizing flows which transform an original simpler distribution to a more complex one. The approach of this thesis is based on a different idea that combines random Fourier features with density matrices to estimate the underlying distribution function. The method can be seen as an approximation of the popular kernel density estimation method but without the inherent computational cost.
The aim of this project is to improve human decision-making using explainability; specifically, how to explain the (un)certainty of machine learning models. Prior research has used uncertainty measures to promote trust and decision-making. However, the direction of explaining why the AI prediction is confident (or not confident) in its prediction needs to be addressed. By explaining the model uncertainty, we can promote trust, improve understanding and improve decision-making for users.
Recent studies demonstrated that the training process of deep neural networks (DNNs) is vulnerable to backdoor attacks if third-party training resources (e.g., samples) are adopted. Specifically, the adversaries intend to embed hidden backdoors into DNNs, where the backdoor can be activated by pre-defined trigger patterns and leading malicious model predictions. My dissertation focuses on poisoning-based backdoor attacks in computer vision. Firstly, I study and propose more stealthy and effective attacks against image classification tasks in both physical and digital spaces. Secondly, I reveal the backdoor threats in visual object tracking, which is representative of critical video-related tasks. Thirdly, I explore how to exploit backdoor attacks as watermark techniques for positive purposes. I design a Python toolbox (i.e., BackdoorBox) that implements representative and advanced backdoor attacks and defenses under a unified and flexible framework, based on which to provide a comprehensive benchmark of existing methods at the end.
It is envisioned that in the near future autonomous systems such as multi-agent systems, will co-exist with humans, e.g., autonomous vehicles will share roads with human drivers. These safety-critical scenarios require formally provable safety guarantees so that the robots will never collide with humans or with each other. It is challenging to provide such guarantees in the real world due to the stochastic environments and inaccurate models of heterogeneous agents including robots and humans. My PhD research investigates decision-making algorithm design for provably-correct safety guarantees in mixed multi-agent systems.
My research focuses on machine models of theory of mind, a set of skills that helps humans cooperate with each other. Because these skills present themselves in behavior, inference-based measurements must be carefully designed to rule out alternate hypotheses. Producing models that display these skills requires an extensive understanding of experiences and mechanisms sufficient for learning, and the models must have robust generalization to be effective in varied domains. To address these problems, I intend to evaluate computational models of ToM using a variety of tests.
Visible-to-Thermal (VT) face translation is an under-studied problem of image-to-image translation that offers an AI-enabled alternative to traditional thermal sensors. Over three phases, my Doctoral Proposal explores developing multimodal deep generative solutions that can be applied towards telemedicine applications. These include the contribution of a novel Thermal Face Contrastive GAN (TFC-GAN), exploration of hybridized diffusion-GAN models, application on real clinical thermal data at the National Institutes of Health, and exploration of strategies for Federated Learning (FL) in heterogenous data settings.
In recent decades, advancements in information technology allowed Artificial Intelligence (AI) systems to predict future outcomes with unprecedented success. This brought the widespread deployment of these methods in many fields, intending to support decision-making. A pressing question is how to make AI systems robust to common challenges in real-life scenarios and trustworthy. In my work, I plan to explore ways to enhance the trustworthiness of AI through the selective classification framework. In this setting, the AI system can refrain from predicting whenever it is not confident enough, allowing it to trade off coverage, i.e. the percentage of instances that receive a prediction, for performance.
Storytelling is an innate part of language-based communication. Today, current events are reported via Open Source Intelligence (OSINT) sources like news websites, blogs, and discussion forums. Scattered and fragmented sources such as these can be better understood when organized as chains of event plot points, or narratives, that have the ability to communicate end-end stories. Though search engines can retrieve aggregated event information, they lack the ability to sequence relevant events together to form narratives about different topics. I propose an AI system inspired by Gustav Freytag’s narrative theory called the Plot Element Pyramid and use knowledge graphs to represent, chain, and reason over narratives from disparately sourced event details to better comprehend convoluted, noisy information about critical events during intelligence analysis.
Representation Learning is the core of Machine Learning and Artificial Intelligence as it summarizes input data points into low dimensional vectors. This low dimensional vectors should be accurate portrayals of the input data, thus it is crucial to find the most effective and robust representation possible for given input as the performance of the ML task is dependent on the resulting representations. In this summary, we discuss an approach to augment representation learning which relies on external knowledge. We briefly describe the shortcoming of the existing techniques and describe how an auxiliary knowledge source could result in obtaining improved representations.
High-performing human teams leverage intelligent and efficient communication and coordination strategies to collaboratively maximize their joint utility. Inspired by teaming behaviors among humans, I seek to develop computational methods for synthesizing intelligent communication and coordination strategies for collaborative multi-robot systems. I leverage both classical model-based control and planning approaches as well as data-driven methods such as Multi-Agent Reinforcement Learning (MARL) to provide several contributions towards enabling emergent cooperative teaming behavior across both homogeneous and heterogeneous (including agents with different capabilities) robot teams.
Meta-learning usually refers to a learning algorithm that learns from other learning algorithms. The problem of uncertainty in the predictions of neural networks shows that the world is only partially predictable and a learned neural network cannot generalize to its ever-changing surrounding environments. Therefore, the question is how a predictive model can represent multiple predictions simultaneously. We aim to provide a fundamental understanding of learning to learn in the contents of Decentralized Neural Networks (Decentralized NNs) and we believe this is one of the most important questions and prerequisites to building an autonomous intelligence machine. To this end, we shall demonstrate several pieces of evidence for tackling the problems above with Meta Learning in Decentralized NNs. In particular, we will present three different approaches to building such a decentralized learning system: (1) learning from many replica neural networks, (2) building the hierarchy of neural networks for different functions, and (3) leveraging different modality experts to learn cross-modal representations.
My research focuses on new techniques in machine learning and game theory to optimally allocate our scarce resources in multi-agent settings to maximize environmental sustainability. Drawing scientific questions from my close partnership with conservation organizations, I have advanced new lines of research in learning and planning under uncertainty, inspired by the low-data, noisy, and dynamic settings faced by rangers on the frontlines of protected areas.
My thesis is focusing on how we can overcome the gap people have against machine learning techniques that require a well-defined application scheme and can produce wrong results. I am planning to discuss the principle of the interaction design that fills such a gap based on my past projects that have explored better interactions for applying machine learning in various fields, such as malware analysis, executive coaching, photo editing, and so on. To this aim, my thesis also shed a light on the limitations of machine learning techniques, like adversarial examples, to highlight the importance of "failure-resistant intelligent interaction."
Although recent network representation learning (NRL) works in text-attributed networks demonstrated superior performance for various graph inference tasks, learning network representations could always raise privacy concerns when nodes represent people or human-related variables. Moreover, standard NRLs that leverage structural information from a graph proceed by first encoding pairwise relationships into learned representations and then analysing its properties. This approach is fundamentally misaligned with problems where the relationships involve multiple points, and topological structure must be encoded beyond pairwise interactions. Fortunately, the machinery of topological data analysis (TDA) and, in particular, simplicial neural networks (SNNs) offer a mathematically rigorous framework to evaluate not only higher-order interactions, but also global invariant features of the observed graph to systematically learn topological structures. It is critical to investigate if the representation outputs from SNNs are more vulnerable compared to regular representation outputs from graph neural networks (GNNs) via pairwise interactions. In my dissertation, I will first study learning the representations with text attributes for simplicial complexes (RT4SC) via SNNs. Then, I will conduct research on two potential attacks on the representation outputs from SNNs: (1) membership inference attack, which infers whether a certain node of a graph is inside the training data of the GNN model; and (2) graph reconstruction attacks, which infer the confidential edges of a text-attributed network. Finally, I will study a privacy-preserving deterministic differentially private alternating direction method of multiplier to learn secure representation outputs from SNNs that capture multi-scale relationships and facilitate the passage from local structure to global invariant features on text-attributed networks.
The widespread adoption of electronic health records (EHRs) has opened up new opportunities for using deep neural networks to enhance healthcare. However, modeling EHR data can be challenging due to its complex properties, such as missing values, data scarcity in multi-hospital systems, and multimodal irregularity. How to tackle various issues in EHRs for improving medical prediction is challenging and under exploration. I separately illustrate my works to address these issues in EHRs and discuss potential future directions.