NIPS Proceedingsβ

Surya Ganguli

9 Papers

  • Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice (2017)
  • Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net (2017)
  • An equivalence between high dimensional Bayes optimal inference and M-estimation (2016)
  • Deep Learning Models of the Retinal Response to Natural Scenes (2016)
  • Exponential expressivity in deep neural networks through transient chaos (2016)
  • Deep Knowledge Tracing (2015)
  • Identifying and attacking the saddle point problem in high-dimensional non-convex optimization (2014)
  • A memory frontier for complex synapses (2013)
  • Short-term memory in neuronal networks through dynamical compressed sensing (2010)