no code implementations • 9 May 2024 • Jessica N. Howard, Ro Jefferson, Anindita Maiti, Zohar Ringel
We systematically integrate out the unlearnable modes of the GP kernel, thereby obtaining an RG flow of the Gaussian Process in which the data plays the role of the energy scale.
no code implementations • 10 Apr 2023 • Aleksandar Bukva, Jurriaan de Gier, Kevin T. Grosvenor, Ro Jefferson, Koenraad Schalm, Eliot Schwander
In this work, we explore the effect of saturation of the tanh activation function along the edge of chaos.
no code implementations • 27 Sep 2021 • Kevin T. Grosvenor, Ro Jefferson
We explicitly construct the quantum field theory corresponding to a general class of deep neural networks encompassing both recurrent and feedforward architectures.
1 code implementation • 14 Jul 2021 • Johanna Erdmenger, Kevin T. Grosvenor, Ro Jefferson
In particular, we quantify the flow of information by explicitly computing the relative entropy or Kullback-Leibler divergence in both the one- and two-dimensional Ising models under decimation RG, as well as in a feedforward neural network as a function of depth.