Physical Sciences and Mathematics Commons^™

Incremental Non-Greedy Clustering At Scale, Nicholas Monath

Doctoral Dissertations

Clustering is the task of organizing data into meaningful groups. Modern clustering applications such as entity resolution put several demands on clustering algorithms: (1) scalability to massive numbers of points as well as clusters, (2) incremental additions of data, (3) support for any user-specified similarity functions. Hierarchical clusterings are often desired as they represent multiple alternative flat clusterings (e.g., at different granularity levels). These tree-structured clusterings provide for both fine-grained clusters as well as uncertainty in the presence of newly arriving data. Previous work on hierarchical clustering does not fully address all three of the aforementioned desiderata. Work on incremental …

Robust Algorithms For Clustering With Applications To Data Integration, Sainyam Galhotra

Doctoral Dissertations

A growing number of data-based applications are used for decision-making that have far-reaching consequences and significant societal impact. Entity resolution, community detection and taxonomy construction are some of the building blocks of these applications and for these methods, clustering is the fundamental underlying concept. Therefore, the use of accurate, robust and scalable methods for clustering cannot be overstated. We tackle the various facets of clustering with a multi-pronged approach described below. 1. While identification of clusters that refer to different entities is challenging for automated strategies, it is relatively easy for humans. We study the robustness of clustering methods that …

Compact Representations Of Uncertainty In Clustering, Craig Stuart Greenberg

Doctoral Dissertations

Flat clustering and hierarchical clustering are two fundamental tasks, often used to discover meaningful structures in data, such as subtypes of cancer, phylogenetic relationships, taxonomies of concepts, and cascades of particle decays in particle physics. When multiple clusterings of the data are possible, it is useful to represent uncertainty in clustering through various probabilistic quantities, such as the distribution over partitions or tree structures, and the marginal probabilities of subpartitions or subtrees. Many compact representations exist for structured prediction problems, enabling the efficient computation of probability distributions, e.g., a trellis structure and corresponding Forward-Backward algorithm for Markov models that model …

Reasoning About User Feedback Under Identity Uncertainty In Knowledge Base Construction, Ariel Kobren

Doctoral Dissertations

Intelligent, automated systems that are intertwined with everyday life---such as Google Search and virtual assistants like Amazon’s Alexa or Apple’s Siri---are often powered in part by knowledge bases (KBs), i.e., structured data repositories of entities, their attributes, and the relationships among them. Despite a wealth of research focused on automated KB construction methods, KBs are inevitably imperfect, with errors stemming from various points in the construction pipeline. Making matters more challenging, new data is created daily and must be integrated with existing KBs so that they remain up-to-date. As the primary consumers of KBs, human users have tremendous potential to …

Development Of A Modeling Algorithm To Predict Lean Implementation Success, Richard Charles Barclay

Doctoral Dissertations

”Lean has become a common term and goal in organizations throughout the world. The approach of eliminating waste and continuous improvement may seem simple on the surface but can be more complex when it comes to implementation. Some firms implement lean with great success, getting complete organizational buy-in and realizing the efficiencies foundational to lean. Other organizations struggle to implement lean. Never able to get the buy-in or traction needed to really institute the sort of cultural change that is often needed to implement change. It would be beneficial to have a tool that organizations could use to assess their …

Machine Learning Techniques Implementation In Power Optimization, Data Processing, And Bio-Medical Applications, Khalid Khairullah Mezied Al-Jabery

Doctoral Dissertations

"The rapid progress and development in machine-learning algorithms becomes a key factor in determining the future of humanity. These algorithms and techniques were utilized to solve a wide spectrum of problems extended from data mining and knowledge discovery to unsupervised learning and optimization. This dissertation consists of two study areas. The first area investigates the use of reinforcement learning and adaptive critic design algorithms in the field of power grid control. The second area in this dissertation, consisting of three papers, focuses on developing and applying clustering algorithms on biomedical data. The first paper presents a novel modelling approach for …

Data Analysis Methods Using Persistence Diagrams, Andrew Marchese

Doctoral Dissertations

In recent years, persistent homology techniques have been used to study data and dynamical systems. Using these techniques, information about the shape and geometry of the data and systems leads to important information regarding the periodicity, bistability, and chaos of the underlying systems. In this thesis, we study all aspects of the application of persistent homology to data analysis. In particular, we introduce a new distance on the space of persistence diagrams, and show that it is useful in detecting changes in geometry and topology, which is essential for the supervised learning problem. Moreover, we introduce a clustering framework directly …

Neuron Clustering For Mitigating Catastrophic Forgetting In Supervised And Reinforcement Learning, Benjamin Frederick Goodrich

Doctoral Dissertations

Neural networks have had many great successes in recent years, particularly with the advent of deep learning and many novel training techniques. One issue that has affected neural networks and prevented them from performing well in more realistic online environments is that of catastrophic forgetting. Catastrophic forgetting affects supervised learning systems when input samples are temporally correlated or are non-stationary. However, most real-world problems are non-stationary in nature, resulting in prolonged periods of time separating inputs drawn from different regions of the input space.

Reinforcement learning represents a worst-case scenario when it comes to precipitating catastrophic forgetting in neural networks. …

Computational Intelligence Based Complex Adaptive System-Of-Systems Architecture Evolution Strategy, Siddharth Agarwal

Doctoral Dissertations

The dynamic planning for a system-of-systems (SoS) is a challenging endeavor. Large scale organizations and operations constantly face challenges to incorporate new systems and upgrade existing systems over a period of time under threats, constrained budget and uncertainty. It is therefore necessary for the program managers to be able to look at the future scenarios and critically assess the impact of technology and stakeholder changes. Managers and engineers are always looking for options that signify affordable acquisition selections and lessen the cycle time for early acquisition and new technology addition. This research helps in analyzing sequential decisions in an evolving …

A Proportionality-Based Approach To Search Result Diversification, Van Bac Dang

Doctoral Dissertations

Search result diversification addresses the problem of queries with unclear information needs. The aim of using diversification techniques is to find a ranking of documents that covers multiple possible interpretations, aspects, or topics for a given query. By explicitly providing diversity in search results, this approach can increase the likelihood that users will find documents relevant to their specific intent, thereby improving effectiveness. This dissertation introduces a new perspective on diversity: diversity by proportionality. We consider a result list more diverse, with respect to some set of topics related to the query, when the ratio between the number of relevant …

Online Multi-Stage Deep Architectures For Feature Extraction And Object Recognition, Derek Christopher Rose

Doctoral Dissertations

Multi-stage visual architectures have recently found success in achieving high classification accuracies over image datasets with large variations in pose, lighting, and scale. Inspired by techniques currently at the forefront of deep learning, such architectures are typically composed of one or more layers of preprocessing, feature encoding, and pooling to extract features from raw images. Training these components traditionally relies on large sets of patches that are extracted from a potentially large image dataset. In this context, high-dimensional feature space representations are often helpful for obtaining the best classification performances and providing a higher degree of invariance to object transformations. …

Adaptive Grid Based Localized Learning For Multidimensional Data, Sheetal Saini

Doctoral Dissertations

Rapid advances in data-rich domains of science, technology, and business has amplified the computational challenges of "Big Data" synthesis necessary to slow the widening gap between the rate at which the data is being collected and analyzed for knowledge. This has led to the renewed need for efficient and accurate algorithms, framework, and algorithmic mechanisms essential for knowledge discovery, especially in the domains of clustering, classification, dimensionality reduction, feature ranking, and feature selection. However, data mining algorithms are frequently challenged by the sparseness due to the high dimensionality of the datasets in such domains which is particularly detrimental to the …

Machine Learning Approaches For Determining Effective Seeds For K -Means Algorithm, Kaveephong Lertwachara

Doctoral Dissertations

In this study, I investigate and conduct an experiment on two-stage clustering procedures, hybrid models in simulated environments where conditions such as collinearity problems and cluster structures are controlled, and in real-life problems where conditions are not controlled. The first hybrid model (NK) is an integration between a neural network (NN) and the k-means algorithm (KM) where NN screens seeds and passes them to KM. The second hybrid (GK) uses a genetic algorithm (GA) instead of the neural network. Both NN and GA used in this study are in their simplest-possible forms.

In the simulated data sets, I investigate two …