Object categorization is one of the fundamental topics in computer vision research. Most current work in object categorization aims to discriminate among generic object classes with gross differences. However, many applications require much finer distinctions. This thesis focuses on the design, evaluation and analysis of learning algorithms for fine- grained...
Semi-supervised clustering aims to improve clustering performance by considering user supervision in the form of pairwise constraints. In this paper, we study the active learning problem of selecting pairwise must-link and cannot-link constraints for semisupervised clustering. We consider active learning in an iterative manner where in each iteration queries are...
Knowledge workers are struggling in the information flood. There is a growing interest in intelligent desktop environments that help knowledge workers organize their daily life. Intelligent desktop environments allow the desktop user to define a set of “activities” that characterize the user’s desktop work. These environments then attempt to identify...
Anomaly detection has been used in variety of applications in practice, including cyber-security, fraud detection and detecting faults in safety critical systems, etc. Anomaly detectors produce a ranked list of statistical anomalies, which are typically examined by human analysts in order to extract the actual anomalies of interest. Unfortunately, most...
This dissertation explores the idea of applying machine learning technologies to help computer users find information and better organize electronic resources, by presenting the research work conducted in the following three applications: FolderPredictor, Stacking Recommendation Engines, and Integrating Learning and Reasoning.
FolderPredictor is an intelligent desktop software tool that helps...
Machine learning encompasses probabilistic and statistical techniques that can build models from large quantities of extensional information (examples) with minimal dependence on intensional information (domain knowledge). This focus of machine learning is reflected in the never-ending quest for "off-the-shelf" classifiers. To generalize to unseen data, however, we must make use...
Many problems in ecology and conservation biology can be formulated and solved using machine learning algorithms for multi-label classification. This dissertation addresses three topics related to predicting the distributions of multiple species. It improves existing methods and proposes a new modeling paradigm to address the multi-species, multi-label problem. The first...
The ability to create reproducible cryptographically secure keys from temporal environments (e.g., images) has the potential to be a contributor to effective cryptographic mechanisms. Due to the noisy nature of these environments, achieving this goal in a user friendly fashion is a very challenging task, especially since there exists a...
Machine learning systems are generally trained offline using ground truth data that has been labeled by experts. However, these batch training methods are not a good fit for many applications, especially in the cases where complete ground truth data is not available for offline training. In addition, batch methods do...
We are witnessing the rise of the data-driven science paradigm, in which massive amounts of data - much of it collected as a side-effect of ordinary human activity - can be analyzed to make sense of the data and to make useful predictions. To fully realize the promise of this...
Structural health monitoring (SHM) systems perform automated non-destructive damage detection and characterization for a variety of large structures including civil structures such as bridges and aerospace structures such as aircrafts and space vehicles. The goals of SHM include preventing catastrophic structural failures, increasing reliability, reducing maintenance costs, and increasing the...
In its simplest form, the process of diagnosis is a decision-making process in which the diagnostician performs a sequence of tests culminating in a diagnostic decision. For example, a physician might perform a series of simple measurements (body tem- perature, weight, etc.) and laboratory measurements (white blood count, CT scan,...
Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
The problem of document classification has been widely studied in machine learning and data mining. In document classification, most of the popular algorithms are based on the bag-of-words representation. Due to the high dimensionality of the bag-of-words representation, significant research has been conducted to reduce the dimensionality via different approaches....
This dissertation explores algorithms for learning ranking functions to efficiently solve search problems, with application to automated planning. Specifically, we consider the frameworks of beam search, greedy search, and randomized search, which all aim to maintain tractability at the cost of not guaranteeing completeness nor optimality. Our learning objective for...
Machine learning applied to computer architecture has rapidly transitioned from a theoretical novelty to being a driving force behind design, control, and simulation in practically all components. These machine-learning-based methodologies are further notable for their scalability to increasingly complex design challenges, which has allowed these methodologies to surpass the prior...
Citizen Science is a paradigm in which volunteers from the general public participate in scientific studies, often by performing data collection. This paradigm is especially useful if the scope of the study is too broad to be performed by a limited number of trained scientists. Although citizen scientists can contribute...
Maintaining the sustainability of the earth’s ecosystems has attracted much attention as these ecosystems are facing more and more pressure from human activities. Machine learning can play an important role in promoting sustainability as a large amount of data is being collected from ecosystems. There are at least three important...
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...
We consider the problem of supervised classification of bird species from audio recordings in a real-world acoustic monitoring scenario (i.e. audio data is collected in the field with an omnidirectional microphone, without human supervision). Obtaining better data about bird activity can assist conservation efforts, and improve our understanding of their...
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)...
This thesis addresses a basic problem in computer vision, that of semantic labeling of images. Our work is aimed at object detection in biological images for evolutionary biology research. In particular, our goal is to detect nematocysts in Scanning Electron Microscope (SEM) images. This biological domain presents challenges for existing...
This paper discusses opportunities for developments in spatial clustering methods to help leverage broad scale community science data for building species distribution models (SDMs). SDMs are critical tools that inform the science and policy needed to mitigate the impacts of climate change on biodiversity. Community science data span spatial and...
Machine learning models for natural language processing have traditionally relied on large numbers of discrete features, built up from atomic categories such as word forms and part-of-speech labels, which are considered completely distinct from each other. Recently however, the advent of dense feature representations coupled with deep learning techniques has...
How can end users efficiently influence the predictions that machine learning systems make on their behalf? Traditional systems rely on users to provide examples of how they want the learning system to behave, but this is not always practical for the user, nor efficient for the learning system. This dissertation...
This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
The study of physical activity is important in improving people’s health as it can help people understand the relationship between physical activity and health. Accelerometers, due to its small size, low cost, convenience and its ability to provide objective information about the frequency, intensity, and duration of physical activity, has...
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...
Learning novel concepts from relational databases is an important problem with applications in several disciplines, such as data management, natural language processing, and bioinformatics. For a learning algorithm to be effective, the input data should be clean and in some desired representation. However, real-world data is usually heterogeneous – the...
Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...
In bioacoustics, automatic animal voice detection and recognition from audio recordings is an emerging topic for animal preservation. Our research focuses on bird bioacoustics, where the goal is to segment bird syllables from the recording and predict the bird species for the syllables. Traditional methods for this task addresses the...
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...
Hop (Humulus lupulus L. var lupulus) is a plant of great cultural significance, used as a medicinal herb for thousands of years, and for flavor and as a preservative in brewing beer. Studies of the medicinal effects of the unique compounds produced by hop have led to interest from the...
The results of a machine learning from user behavior can be thought of as a program, and like all programs, it may need to be debugged. Providing ways for the user to debug it matters because without the ability to fix errors, users may find that the learned program’s errors...
In supervised learning, label information can be provided at different levels of granularity. For small datasets, it is possible to acquire a label for each data instance. However, in the big-data regime, this fine granularity approach is prohibitively costly. For example, in semi-supervised learning, only a limited number of samples...