Now showing items 1-3 of 149

    • Multiplicative Regularization Generalizes Better Than Additive Regularization 

      Dubach, Rafael; Abdallah, Mohamed S.; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2025-07-02)
      We investigate the effectiveness of multiplicative versus additive (L2) regularization in deep neural networks, focusing on convolutional neural networks for classification. While additive methods constrain the sum of ...
    • Position: A Theory of Deep Learning Must Include Compositional Sparsity 

      Danhofer, David A.; D'Ascenso, Davide; Dubach, Rafael; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2025-07-02)
      Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the curse of dimensionality. However, open ...
    • On efficiently computable functions, deep networks and sparse compositionality 

      Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2025-02-01)
      In previous papers [4, 6] we have claimed that for each function which is efficiently Turing computable there exists a deep and sparse network which approximates it arbitrarily well. We also claimed a key role for ...