CBMM Memo Series: Recent submissions

Now showing items 43-45 of 149

    • Loss landscape: SGD can have a better view than GD 

      Poggio, Tomaso; Cooper, Yaim (Center for Brains, Minds and Machines (CBMM), 2020-07-01)
      Consider a loss function L = 􏰀ni=1 l2i with li = f(xi) − yi, where f(x) is a deep feedforward network with R layers, no bias terms and scalar output. Assume the network is overparametrized that is, d >> n, where d is the ...

    • Biologically Inspired Mechanisms for Adversarial Robustness 

      Vuyyuru Reddy, Manish; Banburski, Andrzej; Plant, Nishka; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2020-06-23)
      A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small ...

    • Hierarchically Local Tasks and Deep Convolutional Networks 

      Deza, Arturo; Liao, Qianli; Banburski, Andrzej; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2020-06-24)
      The main success stories of deep learning, starting with ImageNet, depend on convolutional networks, which on certain tasks perform significantly better than traditional shallow classifiers, such as support vector machines. ...