Winter 2018

Winter 2018 agenda


  • January, 11th
    • Project Update: Jawad Mroueh, Detroit Vehicle Project, background
  • January, 18th
    • Project Update: Allie cell, Detroit Blight Project, background
  • January, 25th
    • Competition Launch: HomeAway [in partnership with MSSSISS]


Title: Deep Neural Network Learning

Abstract: In this talk, I will present a variety of learning strategies to deal with different issues in neural network model. In tensor factorized neural network, a tensor factorized error back propagation algorithm is developed to preserve the structure of tensor inputs in layer-wise network during training a classification network. We further present a semi-supervised neural network for domain adaptation which jointly minimizes the divergence between the distributions from labeled and unlabeled data in source and target domains, the reconstruction errors due to an auto-encoder, and the classification errors due to the labeled data. Finally, a deep unfolding inference is proposed to integrate the benefits from probabilistic model and neural network. A deep Bayesian topic model is proposed to improve traditional model based on variational inference. A number of applications and future works will be addressed.

  • February, 15th
    • Invited Speaker: Gautam Nagaraj, Mechanical Engineering
  • February, 22nd
    • Invited Speaker: Mohsen Heidari - EECS


  • March, 1st
    • Project Update: Turning the Corner with Data Driven Detroit (D3)
  • March, 8th
  • March, 15th
    • Invited Speaker: Jonathan Terhorst - Professor of Statistics at the University of Michigan
  • March, 22nd
    • Invited Speaker: David Hong - Graduate Student - EECS
  • March, 29th
    • Invited Speaker: Audra McMillan - Graduate Student - Mathematics


  • April, 5th
    • Invited Speaker:
  • April, 12th
    • Wrap-up Session: lead by Arya Farahi, @aryaf
  • April, 19th
    • MDST Executive Board Election
  • April, 26th
    • Graduation Week - NO MEETING