Search Constraints

Start Over
Filtering by: Contributor Soldatov, Alexey I. Remove constraint Contributor: Soldatov, Alexey I. Decade 2020-2029 Remove constraint Decade: 2020-2029

Search Results

  • Emergent Properties of Animal Social Networks: Five Stories in Five Systems

    Creator:
    Devan-Song, E. Anne
    Abstract:
    Animals aggregate and interact in nonuniform and nonrandom patterns, which lead to group level characteristics that have important evolutionary and ecological consequences. Network analysis provides a useful conceptual framework for linking animal interactions at all scales from dyads to communities, to populations and ecosystems. Despite exciting theoretical and applied advances...
    Resource Type:
    Dissertation
    Full Text:
    dissertation, I examine four aspects of animal social networks and their emergent properties in four

  • Designing Diversity and Inclusion Processes and Tools for Sustainable Open Source

    Creator:
    Guizani, Mariam
    Abstract:
    Over time, Open Source Software (OSS) has become indispensable in the creation and upkeep of software products, serving as the fundamental building block for widely used solutions in our daily lives, including applications that enable communication, entertainment, and productivity. A sustainable OSS ecosystem is one that attracts and retains a...
    Resource Type:
    Dissertation
    Full Text:
    domains, Open Source itself is challenged in terms of the Diversity and Inclusion (D&I) of its community

  • Guided Translation of Algorithmic Notation into Functional Programs

    Creator:
    Fedorin, Danila
    Abstract:
    The use of board games for teaching introductory computer science is a promising recent avenue of research. The goal is to introduce computing concepts through their use in the implementations of simple games, thereby keeping students engaged through their learning process. However, there is a gap between students' algorithmic descriptions...
    Resource Type:
    Masters Thesis
    Full Text:
    -suited for immediate ex- ecution. In this thesis, I present a system aimed at helping students refine

  • Two Sides of a Coin: Adversarial-Based Image Privacy and Defending Against Adversarial Perturbations for Robust CNNs

    Creator:
    Rajabi, Arezoo
    Abstract:
    Emergence of highly accurate Convolutional Neural Networks (CNNs) with the capability to process large datasets, has led to their popularity in many applications, including safety/security-sensitive (e.g. disease recognition, self-driving cars). Despite the high accuracy of convolutional neural networks, they have been found to be susceptible to adversarial noise added to...
    Resource Type:
    Dissertation
    Full Text:
    cloud image storage setting. We propose and evaluate two adversarial-based protection methods: (i) a

  • Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

    Creator:
    Desai, Saurabh Satish
    Abstract:
    Top-performing approaches to embodied AI tasks like point-goal navigation often rely on training agents via reinforcement learning over tens of millions (or even billions) of experiential steps – learning neural agents that map directly from visual observations to actions. In this work, we question whether these extreme training durations are...
    Resource Type:
    Masters Thesis
    Full Text:
    and Computer Science Dean of the Graduate School I understand that my thesis will become part of the

  • Automated Trunk Diameter Measurement

    Creator:
    Sankari, Pico
    Abstract:
    This thesis describes an automated method to estimate tree trunk width in a commer-cial apple orchard. Trunk cross sectional area, which is an important consideration with regards to nutrient uptake, is a feature being integrated in a decision support system for precision Nitrogen management. The data used to generate the...
    Resource Type:
    Honors College Thesis
    Full Text:
    Engineering Toni Doolen, Dean, Oregon State University Honors College I understand that my project will

  • Window Axial Vision Transformer for Image Classification

    Creator:
    Lee, Jisoo
    Abstract:
    Currently, a popular approach to image classification uses the deep Transformer architecture. In a Transformer, the attention mechanism enables the model to learn efficiently with fewer computational resources than the convolutional neural networks (CNNs). In this thesis, we study the sparse attention mechanism widely used in the Transformers developed specifically...
    Resource Type:
    Masters Thesis
    Full Text:
    Science Head of the School of Electrical Engineering and Computer Science Dean of the Graduate School I

  • An Exploration of Used Fuel Sharing in Multi-Reactor Power Plants

    Creator:
    Lilley, Benjamin C.
    Abstract:
    Nuclear fuel management is an optimization problem on many levels. Finding “viable” solutions for the core reload design problem is difficult without expert knowledge and software automation. Small modular reactors with a shared used fuel pool demonstrate a novel opportunity for fuel cycle optimization. A Python package was developed and...
    Resource Type:
    Dissertation
    Full Text:
    the Graduate School I understand that my dissertation will become part of the permanent collection of

  • A case for application-based linear transformers : applied towards text-to-spectrogram

    Creator:
    Agostinelli, Victor
    Abstract:
    Various natural language processing (NLP) tasks necessitate deep models that are fast, efficient, and small based on their ultimate application at the edge or elsewhere. While significant investigation has furthered the efficiency and reduced the size of these models, reducing their downstream latency without significant trade-offs remains a difficult task....
    Resource Type:
    Masters Thesis
    Full Text:
    and Computer Science Dean of the Graduate School I understand that my thesis will become part of the

  • Deep Convolutional Network on Point Clouds for 3D Scene Understanding

    Creator:
    Wu, Wenxuan
    Abstract:
    As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...
    Resource Type:
    Dissertation
    Full Text:
    School I understand that my dissertation will become part of the permanent collection of Oregon State