Search Constraints

Start Over
Filtering by: Creator Wang, Kuen Wu Remove constraint Creator: Wang, Kuen Wu Contributor Li, Fuxin Remove constraint Contributor: Li, Fuxin Degree Name Master of Science (M.S.) Remove constraint Degree Name: Master of Science (M.S.)

Search Results

  • 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:
    − 10. Final test accuracy: ”Stochastic Block ADMM”: 90.39%, ”Wang et al.”:84.67% (averaged over 5 runs

  • Detecting Anomalies in Object Appearance and Motion Dynamics

    Creator:
    Alotaibi, Mazen
    Abstract:
    Machine common sense remains a broad, potentially unbounded problem in AI. Our focus is to move toward AI systems that can develop common-sense reasoning similar to humans to detect anomalies. In particular, we study the problem of detecting the violation of expectations when object appearance or motion dynamics change from...
    Resource Type:
    Capstone Project
    Full Text:
    ://arxiv.org/abs/2206.14651 [7] P. Chu, J. Wang, Q. You, H. Ling, and Z. Liu, “Transmot: Spatial-temporal