Registered Data

[01141] On tensor-based training of neural networks

  • Session Time & Room : 5B (Aug.25, 10:40-12:20) @E802
  • Type : Contributed Talk
  • Abstract : In this work by resorting to the continuous ‘model’ of a shallow neural network, we present a novel training approach, that is based on a suitable approximate solution of a Fredholm integral equation of the first kind. Here, we concentrate on least-squares collocation, functional tensor networks and alternating ridge regression. Application of the algorithm to some supervised learning tasks is on par with other state-of-the-art approaches.
  • Classification : 65R20
  • Format : Talk at Waseda University
  • Author(s) :
    • Patrick Gelß ( Zuse Institute Berlin)
    • Aizhan Issagali ( Freie Universität Berlin)
    • Ralf Kornhuber (Freie Universität Berlin)