Towards Robust Deep Neural Networks

Oct 27, 2018
Timothy E. Wang, Jack Gu, Dhagash Mehta, Xiaojun Zhao, Edgar A. Bernal


  Access Model/Code and Paper
The loss surface of deep linear networks viewed through the algebraic geometry lens

Oct 17, 2018
Dhagash Mehta, Tianran Chen, Tingting Tang, Jonathan D. Hauenstein

* 16 pages (2-columns), 5 figures 

  Access Model/Code and Paper
The Loss Surface of XOR Artificial Neural Networks

Apr 06, 2018
Dhagash Mehta, Xiaojun Zhao, Edgar A. Bernal, David J. Wales

* Phys. Rev. E 97, 052307 (2018) 
* 19 pages, 6 figures. Submitted to journal in Oct, 2017 

  Access Model/Code and Paper
Fixed Points of Belief Propagation -- An Analysis via Polynomial Homotopy Continuation

May 30, 2017
Christian Knoll, Franz Pernkopf, Dhagash Mehta, Tianran Chen


  Access Model/Code and Paper
Perspective: Energy Landscapes for Machine Learning

Mar 23, 2017
Andrew J. Ballard, Ritankar Das, Stefano Martiniani, Dhagash Mehta, Levent Sagun, Jacob D. Stevenson, David J. Wales

* 41 pages, 25 figures. Accepted for publication in Physical Chemistry Chemical Physics, 2017 

  Access Model/Code and Paper
A Collection of Challenging Optimization Problems in Science, Engineering and Economics

Apr 09, 2015
Dhagash Mehta, Crina Grosan

* Accepted as an invited contribution to the special session on Evolutionary Computation for Nonlinear Equation Systems at the 2015 IEEE Congress on Evolutionary Computation (at Sendai International Center, Sendai, Japan, from 25th to 28th May, 2015.) 

  Access Model/Code and Paper