Now showing items 1-3 of 131

    • PCA as a defense against some adversaries 

      Aparne, Gupta; Banburski, Andrzej; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2022-03-30)
      Neural network classifiers are known to be highly vulnerable to adversarial perturbations in their inputs. Under the hypothesis that adversarial examples lie outside of the sub-manifold of natural images, previous work has ...
    • SGD Noise and Implicit Low-Rank Bias in Deep Neural Networks 

      Galanti, Tomer; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2022-03-28)
      We analyze deep ReLU neural networks trained with mini-batch stochastic gradient decent and weight decay. We prove that the source of the SGD noise is an implicit low rank constraint across all of the weight matrices within ...
    • Incorporating Rich Social Interactions Into MDPs 

      Tejwani, Ravi; Kuo, Yen-Ling; Shu, Tianmin; Stankovits, Bennett; Gutfreund, Dan; e.a. (Center for Brains, Minds and Machines (CBMM), International Conference on Robotics and Automation (ICRA), 2022-02-07)
      Much of what we do as humans is engage socially with other agents, a skill that robots must also eventually possess. We demonstrate that a rich theory of social interactions originating from microso- ciology and economics ...