4 Matching Annotations
  1. Jul 2024
    1. for - search - google - high resolution addressing of disaggregated text corpus mapped to graph - search results of interest - high resolution addressing of disaggregated text corpus mapped to graph

      search - google - high resolution addressing of disaggregated text corpus mapped to graph - https://www.google.com/search?q=high+resolution+addressing+of+disaggregated+text+corpus+mapped+to+graph&oq=high+resolution+addressing+of+disaggregated+text+corpus+mapped+to+graph&gs_lcrp=EgZjaHJvbWUyBggAEEUYOTIHCAEQIRigATIHCAIQIRigAdIBCTMzNjEzajBqN6gCALACAA&sourceid=chrome&ie=UTF-8

      to - search results of interest - high resolution addressing of disaggregated text corpus mapped to graph - A New Method for Graph-Based Representation of Text in - The use of a new text representation method to predict book categories based on the analysis of its content resulted in accuracy, precision, recall and an F1- ... - https://hyp.is/H9UAbk46Ee-PT_vokcnTqA/www.mdpi.com/2076-3417/10/12/4081 - Encoding Text Information with Graph Convolutional Networks - According to our understanding, this is the first personality recognition study to model the entire user text information corpus as a heterogeneous graph and ... - https://hyp.is/H9UAbk46Ee-PT_vokcnTqA/www.mdpi.com/2076-3417/10/12/4081

  2. Jun 2023
    1. Recent work in computer vision has shown that common im-age datasets contain a non-trivial amount of near-duplicateimages. For instance CIFAR-10 has 3.3% overlap betweentrain and test images (Barz & Denzler, 2019). This results inan over-reporting of the generalization performance of ma-chine learning systems.

      CIFAR-10 performance results are overestimates since some of the training data is essentially in the test set.

  3. May 2020
  4. Aug 2017
    1. This is a very easy paper to follow, but it looks like their methodology is a simple way to improve performance on limited data. I'm curious how well this is reproduced elsewhere.