Search Constraints

Start Over
Filtering by: Creator Tran, Justin T Remove constraint Creator: Tran, Justin T Contributor sim Qi, Zhongang Remove constraint Contributor sim: Qi, Zhongang

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:
    network are stacked inside a block. The parameters Θt are updated by SGD in a forward-backward pass

  • 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:
    (ln d)1/2 max t,t′  N∑ i=1  m∑ j=1 xijt − m∑ j=1 xijt′ 21/2 (2.15) Putting those