Peng Qi


  • ConvolutionalRBM.m

    When I was doing research on deep learning structures, I was amazed by convolutional RBM when I read about it because it possess the amazing capability of learning object parts and “recovering” missing parts (see Reference). Although Alex Krizhevsky has an implementation of such network in pure CUDA, I think some (like myself) might want to use a more friendly Matlab version to process smaller amount of data with a bit more time-consumption —- so here we are.

    Read more…

  • An Unofficial “Bugfix” for QSlim 2.1

    Note: The method of this post is too naive to be applied in sophisticated applications. So please think twice before applying it to yours.

    QSlim is a light-weight software developed by M. Garland, which can simplify mesh models swiftly, maximally preserving their geodesic properties. However, in my recent use of it I discovered a “bug” regarding redundant faces.

    Read more…