Repository logo

Theses and Dissertations

Permanent URI for this collection

https://hdl.handle.net/10217/100389

Browse

Browsing Theses and Dissertations by Author "Adams, Henry, committee member"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    A framework for resource efficient profiling of spatial model performance
    (Colorado State University. Libraries, 2022) Carlson, Caleb, author; Pallickara, Shrideep, advisor; Pallickara, Sangmi Lee, advisor; Adams, Henry, committee member
    We design models to understand phenomena, make predictions, and/or inform decision-making. This study targets models that encapsulate spatially evolving phenomena. Given a model M, our objective is to identify how well the model predicts across all geospatial extents. A modeler may expect these validations to occur at varying spatial resolutions (e.g., states, counties, towns, census tracts). Assessing a model with all available ground-truth data is infeasible due to the data volumes involved. We propose a framework to assess the performance of models at scale over diverse spatial data collections. Our methodology ensures orchestration of validation workloads while reducing memory strain, alleviating contention, enabling concurrency, and ensuring high throughput. We introduce the notion of a validation budget that represents an upper-bound on the total number of observations that are used to assess the performance of models across spatial extents. The validation budget attempts to capture the distribution characteristics of observations and is informed by multiple sampling strategies. Our design allows us to decouple the validation from the underlying model-fitting libraries to interoperate with models designed using different libraries and analytical engines; our advanced research prototype currently supports Scikit-learn, PyTorch, and TensorFlow. We have conducted extensive benchmarks that demonstrate the suitability of our methodology.
  • Thumbnail Image
    ItemOpen Access
    Applications of topological data analysis to natural language processing and computer vision
    (Colorado State University. Libraries, 2022) Garcia, Jason S., author; Krishnaswamy, Nikhil, advisor; Adams, Henry, committee member; Beveridge, Ross, committee member
    Topological Data Analysis (TDA) uses ideas from topology to study the "shape" of data. It provides a set of tools to extract features, such as holes, voids, and connected components, from complex high-dimensional data. This thesis presents an introductory exposition of the mathematics underlying the two main tools of TDA: Persistent Homology and the MAPPER algorithm. Persistent Homology detects topological features that persist over a range of resolutions, capturing both local and global geometric information. The MAPPER algorithm is a visualization tool that provides a type of dimensional reduction that preserves topological properties of the data by projecting them onto lower dimensional simplicial complexes. Furthermore, this thesis explores recent applications of these tools to natural language processing and computer vision. These applications are divided into two main approaches: In the first approach, TDA is used to extract features from data that is then used as input for a variety of machine learning tasks, like image classification or visualizing the semantic structure of text documents. The second approach, applies the tools of TDA to the machine learning algorithms themselves. For example, using MAPPER to study how structure emerges in the weights of a trained neural network. Finally, the results of several experiments are presented. These include using Persistent Homology for image classification, and using MAPPER to visual the global structure of these data sets. Most notably, the MAPPER algorithm is used to visualize vector representations of contextualized word embeddings as they move through the encoding layers of the BERT-base transformer model.
  • Thumbnail Image
    ItemOpen Access
    Convex and non-convex optimization using centroid-encoding for visualization, classification, and feature selection
    (Colorado State University. Libraries, 2022) Ghosh, Tomojit, author; Kirby, Michael, advisor; Anderson, Charles, committee member; Ben-Hur, Asa, committee member; Adams, Henry, committee member
    Classification, visualization, and feature selection are the three essential tasks of machine learning. This Ph.D. dissertation presents convex and non-convex models suitable for these three tasks. We propose Centroid-Encoder (CE), an autoencoder-based supervised tool for visualizing complex and potentially large, e.g., SUSY with 5 million samples and high-dimensional datasets, e.g., GSE73072 clinical challenge data. Unlike an autoencoder, which maps a point to itself, a centroid-encoder has a modified target, i.e., the class centroid in the ambient space. We present a detailed comparative analysis of the method using various data sets and state-of-the-art techniques. We have proposed a variation of the centroid-encoder, Bottleneck Centroid-Encoder (BCE), where additional constraints are imposed at the bottleneck layer to improve generalization performance in the reduced space. We further developed a sparse optimization problem for the non-linear mapping of the centroid-encoder called Sparse Centroid-Encoder (SCE) to determine the set of discriminate features between two or more classes. The sparse model selects variables using the 1-norm applied to the input feature space. SCE extracts discriminative features from multi-modal data sets, i.e., data whose classes appear to have multiple clusters, by using several centers per class. This approach seems to have advantages over models which use a one-hot-encoding vector. We also provide a feature selection framework that first ranks each feature by its occurrence, and the optimal number of features is chosen using a validation set. CE and SCE are models based on neural network architectures and require the solution of non-convex optimization problems. Motivated by the CE algorithm, we have developed a convex optimization for the supervised dimensionality reduction technique called Centroid Component Retrieval (CCR). The CCR model optimizes a multi-objective cost by balancing two complementary terms. The first term pulls the samples of a class towards its centroid by minimizing a sample's distance from its class centroid in low dimensional space. The second term pushes the classes by maximizing the scattering volume of the ellipsoid formed by the class-centroids in embedded space. Although the design principle of CCR is similar to LDA, our experimental results show that CCR exhibits performance advantages over LDA, especially on high-dimensional data sets, e.g., Yale Faces, ORL, and COIL20. Finally, we present a linear formulation of Centroid-Encoder with orthogonality constraints, called Principal Centroid Component Analysis (PCCA). This formulation is similar to PCA, except the class labels are used to formulate the objective, resulting in the form of supervised PCA. We show the classification and visualization experiments results with this new linear tool.
  • Thumbnail Image
    ItemOpen Access
    COVID-19 misinformation on Twitter: the role of deceptive support
    (Colorado State University. Libraries, 2022) Hashemi Chaleshtori, Fateme, author; Ray, Indrakshi, advisor; Anderson, Charles W., committee member; Malaiya, Yashwant K., committee member; Adams, Henry, committee member
    Social media platforms like Twitter are a major dissemination point for information and the COVID-19 pandemic is no exception. But not all of the information comes from reliable sources, which raises doubts about their validity. In social media posts, writers reference news articles to gain credibility by leveraging the trust readers have in reputable news outlets. However, there is not always a positive correlation between the cited article and the social media posting. Targeting the Twitter platform, this study presents a novel pipeline to determine whether a Tweet is indeed supported by the news article it refers to. The approach follows two general objectives: to develop a model capable of detecting Tweets containing claims that are worthy of fact-checking and then, to assess whether the claims made in a given Tweet are supported by the news article it cites. In the event that a Tweet is found to be trustworthy, we extract its claim via a sequence labeling approach. In doing so, we seek to reduce the noise and highlight the informative parts of a Tweet. Instead of detecting erroneous and invalid information by analyzing the propagation patterns or ensuing examination of Tweets against already proven statements, this study aims to identify reliable support (or lack thereof) before misinformation spreads. Our research reveals that 14.5% of the Tweets are not factual and therefore not worth checking. An effective filter like this is especially useful when looking at a platform such as Twitter, where hundreds of thousands of posts are created every day. Further, our analysis indicates that among the Tweets which refer to a news article as evidence of a factual claim, at least 1% of those Tweets are not substantiated by the article, and therefore mislead the reader.