S133 - Learning to map between ferns with differentiable binary embedding networks
Max Blendowski, Mattias P. Heinrich
Current deep learning methods are based on the repeated, expensive application of convolutions with parameter-intensive weight matrices. In this work, we present a novel concept that enables the application of differentiable random ferns in end-to-end networks. It can then be used as multiplication-free convolutional layer alternative in deep network architectures. Our experiments on the binary classification task of the TUPAC\'16 challenge demonstrate improved results over the state-of-the-art binary XNOR net and only slightly worse performance than its 2x more parameter intensive floating point CNN counterpart.
Poster Session #5 - 9:30 - 11:00 UTC-4 (Wednesday)