Search Constraints

Start Over
Filtering by: Creator Stash, Karen M. Remove constraint Creator: Stash, Karen M. Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • Calibrating the highway safety manual predictive methods for Oregon rural state highways

    Creator:
    Xie, Fei
    Abstract:
    The first edition of the Highway Safety Manual (HSM) provides a quantitative approach to predict the safety of transportation facilities based on the recently developed scientific methods. This approach, known as the predictive method, was developed for several states in the United States. Due to differences in driver population, weather...
    Resource Type:
    Masters Thesis
    Full Text:
    : _____________________________________________________________________ Karen K. Dixon The first edition of the Highway Safety Manual (HSM) provides a quantitative

  • Learning ranking functions for efficient search

    Creator:
    Xu, Yuehua
    Abstract:
    This dissertation explores algorithms for learning ranking functions to efficiently solve search problems, with application to automated planning. Specifically, we consider the frameworks of beam search, greedy search, and randomized search, which all aim to maintain tractability at the cost of not guaranteeing completeness nor optimality. Our learning objective for...
    Resource Type:
    Dissertation
    Full Text:
    shape my research work. I also thank Karen Dixon for taking her time off to serve as Graduate Council

  • Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties

    Creator:
    Dodge, Jonathan E.
    Abstract:
    Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools (e.g., a professional auditor, a developer, and an end user all have different needs). We posit that it is possible to provide...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . 180 M Data Appendix - CNNs poisoned by perception/action . . . . . . . . . . . . 182 TABLE OF

  • A Study of Temporal Convolutional Neural Networks for Music Language Modeling as Applied to Automatic Music Transcription

    Creator:
    Meyn, Matthew
    Abstract:
    Automatic music transcription (AMT) is the task, given an acoustic representation of music, to recover a symbolic notation of the written notes expressed by the sound. Transcribing music with multiple notes sounding simultaneously is difficult for both humans and machines. Much existing work on AMT has focused on suitable acoustic...
    Resource Type:
    Capstone Project
    Full Text:
    requirement. For a kernel k of dimensions m by n, the kernel weights in every position that does not precede

  • 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
    Full Text:
    Environments (MCE). We use ‘m’ to indicate the activate mode/action required in that state. Given M = 4 , we

  • Learning and Improving Policies for Probabilistic Planning Problems

    Creator:
    Issakkimuthu, Murugeswari
    Abstract:
    In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
    Resource Type:
    Dissertation
    Full Text:
    . The output layer ZL = {zL0 , zL1 , zL2 , . . . , zLm} contains m + 1 nodes, where zL1 , . . . , zLm

  • Advances in Simultaneous Translation

    Creator:
    Zheng, Renjie
    Abstract:
    Simultaneous translation, which translates concurrently with the source language speech, is widely used in many scenarios including multilateral organizations. However, it is well known to be one of the most challenging tasks for humans due to the simultaneous perception and production in two languages. On the other hand, simultaneous translation...
    Resource Type:
    Dissertation
    Full Text:
    , ..., y ∗ m) goes through the same self-attention to generate hidden self-attended state sequence c

  • Leveraging Structures of the Data in Deep Learning

    Creator:
    Li, Xingyi
    Abstract:
    The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
    Resource Type:
    Dissertation
    Full Text:
    equivalent to the size of the convolutional filter and m represents the number of such parts (size of the

  • Coordination for Scalable Multiple Robot Planning Under Temporal Uncertainty

    Creator:
    Marcon dos Santos, Gilberto
    Abstract:
    This dissertation incorporates coalition formation and probabilistic planning towards a domain-independent automated planning solution scalable to multiple heterogeneous robots in complex domains. The first research direction investigates the effectiveness of Task Fusion and introduces heuristics that improve task allocation and result in better quality plans, while requiring lower computational cost...
    Resource Type:
    Dissertation

  • Action Segmentation in Videos: Deep Models, Prediction Diffusion, and Deep-Temporal Augmentations

    Creator:
    Aziere, Nicolas
    Abstract:
    This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...
    Resource Type:
    Dissertation