Publications: Recent submissions

Now showing items 97-99 of 160

    • Theory II: Landscape of the Empirical Risk in Deep Learning 

      Poggio, Tomaso; Liao, Qianli (Center for Brains, Minds and Machines (CBMM), arXiv, 2017-03-30)
      Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at least for the most successful Deep ...

    • Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning 

      Lotter, William; Kreiman, Gabriel; Cox, David (Center for Brains, Minds and Machines (CBMM), arXiv, 2017-03-01)
      While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning—leveraging unlabeled examples to learn about the structure of a domain — remains ...

    • Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets 

      Tachetti, Andrea; Voinea, Stephen; Evangelopoulos, Georgios (Center for Brains, Minds and Machines (CBMM), arXiv, 2017-03-13)
      The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar ...