Physical Sciences and Mathematics Commons^™

The Performance Of Random Prototypes In Hierarchical Models Of Vision, Kendall Lee Stewart

Dissertations and Theses

I investigate properties of HMAX, a computational model of hierarchical processing in the primate visual cortex. High-level cortical neurons have been shown to respond highly to particular natural shapes, such as faces. HMAX models this property with a dictionary of natural shapes, called prototypes, that respond to the presence of those shapes. The resulting set of similarity measurements is an effective descriptor for classifying images. Curiously, prior work has shown that replacing the dictionary of natural shapes with entirely random prototypes has little impact on classification performance. This work explores that phenomenon by studying the performance of random prototypes on …

Evaluating The Intrinsic Similarity Between Neural Networks, Stephen Charles Ashmore

Graduate Theses and Dissertations

We present Forward Bipartite Alignment (FBA), a method that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks contain complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data may still generalize differently. FBA enables a diversity of applications, including visualization and canonicalization of neural networks, ensembles, and cross-over between unrelated neural networks in evolutionary optimization. We describe the FBA algorithm, and describe implementations for three applications: genetic algorithms, visualization, and ensembles. We demonstrate FBA's usefulness by comparing a …

Detecting, Modeling, And Predicting User Temporal Intention, Hany M. Salaheldeen

Computer Science Theses & Dissertations

The content of social media has grown exponentially in the recent years and its role has evolved from narrating life events to actually shaping them. Unfortunately, content posted and shared in social networks is vulnerable and prone to loss or change, rendering the context associated with it (a tweet, post, status, or others) meaningless. There is an inherent value in maintaining the consistency of such social records as in some cases they take over the task of being the first draft of history as collections of these social posts narrate the pulse of the street during historic events, protest, riots, …

Information Filtering By Multiple Examples, Mingzhu Zhu

Dissertations

A key to successfully satisfy an information need lies in how users express it using keywords as queries. However, for many users, expressing their information needs using keywords is difficult, especially when the information need is complex. Search By Multiple Examples (SBME), a promising method for overcoming this problem, allows users to specify their information needs as a set of relevant documents rather than as a set of keywords.

Most of the studies on SBME adopt the Positive Unlabeled learning (PU learning) techniques by treating the user's provided examples (denoted as query examples) as positive set and the entire data …

Neuroscience-Inspired Dynamic Architectures, Catherine Dorothy Schuman

Doctoral Dissertations

Biological brains are some of the most powerful computational devices on Earth. Computer scientists have long drawn inspiration from neuroscience to produce computational tools. This work introduces neuroscience-inspired dynamic architectures (NIDA), spiking neural networks embedded in a geometric space that exhibit dynamic behavior. A neuromorphic hardware implementation based on NIDA networks, Dynamic Adaptive Neural Network Array (DANNA), is discussed. Neuromorphic implementations are one alternative/complement to traditional von Neumann computation. A method for designing/training NIDA networks, based on evolutionary optimization, is introduced. We demonstrate the utility of NIDA networks on classification tasks, a control task, and an anomaly detection task. There …

Feature Identification And Reduction For Improved Generalization Accuracy In Secondary-Structure Prediction Using Temporal Context Inputs In Machine-Learning Models, Matthew Benjamin Seeley

Theses and Dissertations

A protein's properties are influenced by both its amino-acid sequence and its three-dimensional conformation. Ascertaining a protein's sequence is relatively easy using modern techniques, but determining its conformation requires much more expensive and time-consuming techniques. Consequently, it would be useful to identify a method that can accurately predict a protein's secondary-structure conformation using only the protein's sequence data. This problem is not trivial, however, because identical amino-acid subsequences in different contexts sometimes have disparate secondary structures, while highly dissimilar amino-acid subsequences sometimes have identical secondary structures. We propose (1) to develop a set of metrics that facilitates better comparisons between …

Using Instance-Level Meta-Information To Facilitate A More Principled Approach To Machine Learning, Michael Reed Smith

Theses and Dissertations

As the capability for capturing and storing data increases and becomes more ubiquitous, an increasing number of organizations are looking to use machine learning techniques as a means of understanding and leveraging their data. However, the success of applying machine learning techniques depends on which learning algorithm is selected, the hyperparameters that are provided to the selected learning algorithm, and the data that is supplied to the learning algorithm. Even among machine learning experts, selecting an appropriate learning algorithm, setting its associated hyperparameters, and preprocessing the data can be a challenging task and is generally left to the expertise of …

Epistemological Databases For Probabilistic Knowledge Base Construction, Michael Louis Wick

Doctoral Dissertations

Knowledge bases (KB) facilitate real world decision making by providing access to structured relational information that enables pattern discovery and semantic queries. Although there is a large amount of data available for populating a KB; the data must first be gathered and assembled. Traditionally, this integration is performed automatically by storing the output of an information extraction pipeline directly into a database as if this prediction were the ``truth.'' However, the resulting KB is often not reliable because (a) errors accumulate in the integration pipeline, and (b) they persist in the KB even after new information arrives that could rectify …

Learning With Joint Inference And Latent Linguistic Structure In Graphical Models, Jason Narad

Doctoral Dissertations

Constructing end-to-end NLP systems requires the processing of many types of linguistic information prior to solving the desired end task. A common approach to this problem is to construct a pipeline, one component for each task, with each system's output becoming input for the next. This approach poses two problems. First, errors propagate, and, much like the childhood game of "telephone", combining systems in this manner can lead to unintelligible outcomes. Second, each component task requires annotated training data to act as supervision for training the model. These annotations are often expensive and time-consuming to produce, may differ from each …

Leveraging Contextual Relationships Between Objects For Localization, Clinton Leif Olson

Dissertations and Theses

Object localization is currently an active area of research in computer vision. The object localization task is to identify all locations of an object class within an image by drawing a bounding box around objects that are instances of that class. Object locations are typically found by computing a classification score over a small window at multiple locations in the image, based on some chosen criteria, and choosing the highest scoring windows as the object bounding-boxes. Localization methods vary widely, but there is a growing trend towards methods that are able to make localization more accurate and efficient through the …

Cancer Risk Prediction With Next Generation Sequencing Data Using Machine Learning, Nihir Patel

Theses

The use of computational biology for next generation sequencing (NGS) analysis is rapidly increasing in genomics research. However, the effectiveness of NGS data to predict disease abundance is yet unclear. This research investigates the problem in the whole exome NGS data of the chronic lymphocytic leukemia (CLL) available at dbGaP. Initially, raw reads from samples are aligned to the human reference genome using burrows wheeler aligner. From the samples, structural variants, namely, Single Nucleotide Polymorphism (SNP) and Insertion Deletion (INDEL) are identified and are filtered using SAMtools as well as with Genome Analyzer Tool Kit (GATK). Subsequently, the variants are …

Characterization Of Prose By Rhetorical Structure For Machine Learning Classification, James Java

CCE Theses and Dissertations

Measures of classical rhetorical structure in text can improve accuracy in certain types of stylistic classification tasks such as authorship attribution. This research augments the relatively scarce work in the automated identification of rhetorical figures and uses the resulting statistics to characterize an author's rhetorical style. These characterizations of style can then become part of the feature set of various classification models.

Our Rhetorica software identifies 14 classical rhetorical figures in free English text, with generally good precision and recall, and provides summary measures to use in descriptive or classification tasks. Classification models trained on Rhetorica's rhetorical measures paired with …

Modeling User Transportation Patterns Using Mobile Devices, Erfan Davami

Electronic Theses and Dissertations

Participatory sensing frameworks use humans and their computing devices as a large mobile sensing network. Dramatic accessibility and affordability have turned mobile devices (smartphone and tablet computers) into the most popular computational machines in the world, exceeding laptops. By the end of 2013, more than 1.5 billion people on earth will have a smartphone. Increased coverage and higher speeds of cellular networks have given these devices the power to constantly stream large amounts of data. Most mobile devices are equipped with advanced sensors such as GPS, cameras, and microphones. This expansion of smartphone numbers and power has created a sensing …

Reverse Engineering The Human Brain: An Evolutionary Computation Approach To The Analysis Of Fmri, Nicholas Allgaier

Graduate College Dissertations and Theses

The field of neuroimaging has truly become data rich, and as such, novel analytical methods capable of gleaning meaningful information from large stores of imaging data are in high demand. Those methods that might also be applicable on the level of individual subjects, and thus potentially useful clinically, are of special interest. In this dissertation we introduce just such a method, called nonlinear functional mapping (NFM), and demonstrate its application in the analysis of resting state fMRI (functional Magnetic Resonance Imaging) from a 242-subject subset of the IMAGEN project, a European study of risk-taking behavior in adolescents that includes longitudinal …

Visual Saliency Estimation : A Pre-Attentive Cognitive And Context-Aware Approach, Amanda Shannon Danko

Legacy Theses & Dissertations (2009 - 2024)

At each glance, biological vision systems organize a tremendous amount of input and

Singular Value Computation And Subspace Clustering, Qiao Liang

Theses and Dissertations--Mathematics

In this dissertation we discuss two problems. In the first part, we consider the problem of computing a few extreme eigenvalues of a symmetric definite generalized eigenvalue problem or a few extreme singular values of a large and sparse matrix. The standard method of choice of computing a few extreme eigenvalues of a large symmetric matrix is the Lanczos or the implicitly restarted Lanczos method. These methods usually employ a shift-and-invert transformation to accelerate the speed of convergence, which is not practical for truly large problems. With this in mind, Golub and Ye proposes an inverse-free preconditioned Krylov subspace method, …

Seavipers - Computer Vision And Inertial Position Reference Sensor System (Cviprss), Justin Lee Erdman

LSU Doctoral Dissertations

This work describes the design and development of an optical, Computer Vision (CV) based sensor for use as a Position Reference System (PRS) in Dynamic Positioning (DP). Using a combination of robotics and CV techniques, the sensor provides range and heading information to a selected reference object. The proposed optical system is superior to existing ones because it does not depend upon special reflectors nor does it require a lengthy set-up time. This system, the Computer Vision and Inertial Position Reference Sensor System (CVIPRSS, pronounced \nickname), combines a laser rangefinder, infrared camera, and a pan--tilt unit with the robust TLD …