Asosiy kontentga oʻtish
Boshqa

Report on scipost_202109_00014v1

Johanna ErdmengerInstitute for Theoretical Physics and Astrophysics and Würzburg -DresdenKevin T. GrosvenorMax Planck Institute for the Physics of Complex Systems and Würzburg-Dresden Cluster of Excellence ct.qmat, Nöthnitzer Str. 38, 01187 Dresden, GermanyRo JeffersonNordita KTH Royal Institute of Technology and Stockholm University , Hannes Alfvéns väg 12 , SE-106 91 Stockholm , Sweden
2021en
ABI

Annotatsiya

We investigate the analogy between the renormalization group (RG) and deep neural networks, wherein subsequent layers of neurons are analogous to successive steps along the RG.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.We observe qualitatively identical behavior characterized by the monotonic increase to a parameter-dependent asymptotic value.On the quantum field theory side, the monotonic increase confirms the connection between the relative entropy and the c-theorem.For the neural networks, the asymptotic behavior may have implications for various information maximization methods in machine learning, as well as for disentangling compactness and generalizability.Furthermore, while both the two-dimensional Ising model and the random neural networks we consider exhibit non-trivial critical points, the relative entropy appears insensitive to the phase structure of either system.In this sense, more refined probes are required in order to fully elucidate the flow of information in these models.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar