Search Constraints

Start Over
Filtering by: Creator Zégre, Nicolas P. Remove constraint Creator: Zégre, Nicolas P. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • 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
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Nicolas Aziere for

  • Incorporating and Learning Behavior Constraints for Sequential Decision Making

    Creator:
    Pinto, Jervis
    Abstract:
    Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
    Resource Type:
    Dissertation
    Full Text:
    Constraints for Sequential Decision Making Abstract approved: Alan P. Fern Writing a program that performs

  • Mental Models of Mere Mortals with Explanations of Reinforcement Learning

    Creator:
    Anderson, Andrew A.
    Abstract:
    How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated...
    Resource Type:
    Masters Thesis
    Full Text:
    checking with Levene’s test that the variances were not significantly2 different (F (3, 120) = 0.4252, p

  • Methods for Detection and Recovery of Out-of-Distribution Examples

    Creator:
    Ratzlaff, Neale J.
    Abstract:
    Deep neural networks currently comprise the backbone of many applications where safety is a critical concern, for example: autonomous driving and medical diagnostics. Unfortunately these systems currently fail to detect out-of-distribution (OOD) inputs and can be prone to making dangerous errors when exposed to them. In addition, these same systems...
    Resource Type:
    Masters Thesis
    Full Text:
    discriminator forces Q(q|s) to be well-distributed and close to P . . . . . 14 2.2 Results of HyperGAN on the

  • Branched Covering Space Construction and Visualization

    Creator:
    Golbabaei, Sanaz
    Abstract:
    Branched covering spaces are a mathematical concept which originates from complex analysis and topology and has found applications in tensor field topology and geometry re-meshing. Given a manifold surface and an N-way rotational symmetry field, a branched covering space is a manifold surface that has an N-to-1 map to the...
    Resource Type:
    Masters Thesis
    Full Text:
    topological space C together with a continuous surjective map: p : C→ X such that for every x ∈ X , there

  • Corporate involvement in FOSS projects : an in-depth look at corporate contributions and implications for project governance

    Creator:
    Forrest, Darren J.
    Abstract:
    Free / Open Source Software developers come from a myriad of different backgrounds. While some contribute for personal reasons, many become involved because they receive compensation from corporations or foundations. The motivation for participating in a project can have dramatic impacts on how and what contribution an individual makes. These...
    Resource Type:
    Masters Thesis
    Full Text:
    , Working Conference on (p. 90). Los Alamitos, CA, USA: IEEE Computer Society. doi:http

  • Incorporating labeled features into image classification using generalized expectation

    Creator:
    Moore, Travis
    Abstract:
    Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
    Resource Type:
    Masters Thesis
    Full Text:
    models the conditional distribution P (~Y | ~X) as a product of factors, where each factor is the

  • SIDUR--a formalism for structuring knowledge bases

    Creator:
    Kogan, Dan D.
    Abstract:
    A new class of information intensive applications is emerging [Fuch82; Ohsu82] for which neither Artificial Intelligence (AI) nor Database technologies alone are well suited. Database systems do not provide the general inferential capabilities required for problem solving, while AI techniques have not been adapted to handle massive amounts of structured...
    Resource Type:
    Masters Thesis
    Full Text:
    /WorkOrder) (cardinalities: 1 , 3 <P>) Figure 3- Situation with closed world interpretation. The meaning

  • Image Based Crypto

    Creator:
    Basa, Gungor
    Abstract:
    The ability to create reproducible cryptographically secure keys from temporal environments (e.g., images) has the potential to be a contributor to effective cryptographic mechanisms. Due to the noisy nature of these environments, achieving this goal in a user friendly fashion is a very challenging task, especially since there exists a...
    Resource Type:
    Masters Thesis
    Full Text:
    another position based scheme. 8 Chapter 3: Notation and Preliminaries Notation: ~f , ~b, H, P , I

  • 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:
    , Nicolas, Tieqiao, and Ajay for giving me insight into this study and feedback. Thanks should go to Dr