DeepAI AI Chat
Log In Sign Up

An Outer-approximation Guided Optimization Approach for Constrained Neural Network Inverse Problems

by   Myun-Seok Cheon, et al.

This paper discusses an outer-approximation guided optimization method for constrained neural network inverse problems with rectified linear units. The constrained neural network inverse problems refer to an optimization problem to find the best set of input values of a given trained neural network in order to produce a predefined desired output in presence of constraints on input values. This paper analyzes the characteristics of optimal solutions of neural network inverse problems with rectified activation units and proposes an outer-approximation algorithm by exploiting their characteristics. The proposed outer-approximation guided optimization comprises primal and dual phases. The primal phase incorporates neighbor curvatures with neighbor outer-approximations to expedite the process. The dual phase identifies and utilizes the structure of local convex regions to improve the convergence to a local optimal solution. At last, computation experiments demonstrate the superiority of the proposed algorithm compared to a projected gradient method.


page 1

page 2

page 3

page 4


An artificial neural network approximation for Cauchy inverse problems

A novel artificial neural network method is proposed for solving Cauchy ...

A nonsmooth primal-dual method with simultaneous adaptive PDE constraint solver

We introduce an efficient first-order primal-dual method for the solutio...

Convolutional neural networks in phase space and inverse problems

We study inverse problems consisting on determining medium properties us...

Predictive online optimisation with applications to optical flow

Online optimisation revolves around new data being introduced into a pro...

An Analytic Solution to the Inverse Ising Problem in the Tree-reweighted Approximation

Many iterative and non-iterative methods have been developed for inverse...

Speeding-Up Back-Propagation in DNN: Approximate Outer Product with Memory

In this paper, an algorithm for approximate evaluation of back-propagati...