Search Constraints

Start Over
Filtering by: Creator Steinkamp, Matthew J. Remove constraint Creator: Steinkamp, Matthew J. Committee Member Wong, Weng-Keen Remove constraint Committee Member: Wong, Weng-Keen

Search Results

  • Effects of spatial scale and heterogeneity on avian occupancy dynamics and population trends in forested mountain landscapes

    Creator:
    Frey, Sarah J. K.
    Abstract:
    Population trends and patterns in species distributions are the major currencies used to examine responses by biodiversity to changing environments. Effective conservation recommendations require that models of both distribution dynamics and population trends accurately reflect reality. However, identification of the appropriate temporal and spatial scales of animal response, and then...
    Resource Type:
    Dissertation
    Full Text:
    MICROTOPOGRAPHY Sarah J. K. Frey, Adam S. Hadley, Sherri L. Johnson, Mark Schulze, Julia Jones, Matthew

  • Multi-instance multi-label learning : algorithms and applications to bird bioacoustics

    Creator:
    Briggs, Forrest
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    University. We would also like to thank Matthew Betts, Sarah Frey, Adam Hadley, and Jay Sexsmith for their

  • Creating, Understanding and Applying Machine Learning Models of Multiple Species

    Creator:
    Griffioen, Arwen Twinkle E.
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    term contains two penalty terms. The first is an L2 (ridge) penalty ‖𝛽‖2 2 = ∑ 𝛽𝑗 2𝐽 𝑗=1

  • Classifier Chains for Multi-Label Classification with Incomplete Labels

    Creator:
    Almuallim, Jafer
    Abstract:
    Many methods have been explored in the literature of multi-label learning, ranging from simple problem transformation to more complex method that capture correlation among labels. However, mostly all existing works do not address the challenge with incomplete label data. The goal of this project is to extend the work of...
    Resource Type:
    Capstone Project
    Full Text:
    number of labels associated with an instance defined as followed: Lcard = 1 N ∑N i=1 ∑L j=1 ti 1http

  • Re-understanding Finite-State Representations of Recurrent Policy Networks

    Creator:
    Danesh, Mohamad H.
    Abstract:
    We propose an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM) and then analyzing the equivalent minimized FSM. While this led to interesting insights, the minimization process can obscure a deeper understanding...
    Resource Type:
    Masters Thesis

  • Understanding the Application and Benefits of Learning-based Methods in Nuclear Science and Engineering

    Creator:
    Gómez Fernández, Mario Enrique
    Abstract:
    Known as the fourth industrial revolution, digitization is an ongoing trend in all fields, in which various industries are integrating information technologies to support and improve their businesses. Nuclear technology industries have also increased their interest in data-driven methods by leveraging the potential of pattern recognition to identify anomalies and...
    Resource Type:
    Dissertation

  • Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

    Creator:
    Khorram, Saeed
    Abstract:
    In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
    Resource Type:
    Masters Thesis
    Full Text:
    M ,S 1 2 ‖X −MS‖2F (2.8) subject to Mij ≥ 0, Sij ≥ 0 ∀i, j where r is the decomposition rank and

  • Investigating Latent State and Uncertainty Representations in Reinforcement Learning

    Creator:
    Koul, Anurag
    Abstract:
    Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
    Resource Type:
    Dissertation

  • Interpretable Machine Learning: Applications in Biology and Genomics

    Creator:
    Danaee, Padideh
    Abstract:
    Machine learning (ML) and deep learning (DL) models impact our daily lives with applications in natural language modeling, image analysis, healthcare, genomics, and bioinformatics. The exponential growth of biological sequence data necessitates accompanying advances in computational methods. Although deep learning is highly effective for detecting and classifying biological sequences, challenges...
    Resource Type:
    Dissertation
    Full Text:
    that has base pair (i, j) with all other base pairs such that i < i0 < j0 < j as with (i0, j0), or i

  • Relational Learning over Dirty Data Using Data Constraints

    Creator:
    Lee, Ga Young
    Abstract:
    Real-world datasets are dirty and contain many errors. Examples of these issues are violations of integrity constraints, duplicates, and inconsistencies in representing data values and entities. Applying machine learning on dirty databases may lead to inaccurate results. Users have to spend a lot of time and effort repairing data errors...
    Resource Type:
    Masters Thesis
    Full Text:
    . Lastly, my family members in Seoul and Chicago and my partner, Matthew Castillon, never stopped