Representations in deep learning and quantum many-body physics (Dr. P. Wittek)

  • Date: Jun 19, 2017
  • Time: 02:00 PM - 03:00 PM (Local Time Germany)
  • Speaker: Dr. Peter Wittek
  • ICFO The Institute of Photonic Sciences, Castelldefels, Spain
  • Room: Herbert Walther Lecture Hall
  • Host: MPQ, Theory Division
Representation is of central importance in both quantum many-body physics and machine learning.

Until the advent of deep learning, a key task in machine learning was feature engineering, that is, constructing a space of raw data that would allow a learning algorithm to identify patterns. We see similar 'hand-crafted' representations in physics: for instance, the entanglement spectra often reveals phase transitions. Deep architectures in machine learning automated the extraction of representation, and tensor networks fulfil a similar role in many-body physics. Results proving equivalence between the two paradigms are beginning to emerge. In this talk, we present work-in-progress results on the correspondence between hierarchical tensor networks and deep learning architectures.

Go to Editor View