Robustness is a desirable property in a neural network. Informally, robustness can be described as ‘resilience to perturbations in the input’. Said differently, a neural network is robust if small changes to the input produce small or no changes to the output. In particular, if the network is a classifier, robustness means that inputs close to each other should be assigned the same class by the network.

The Unit Commitment Problem (UCP) [1] in power systems is the problem of scheduling the optimal number of power generating units (or simply units) to meet the total demand in each time period (or slot) of a planning horizon. The UCP is an optimization problem that aims to minimize the running costs, startup costs and shutdown costs of the units while satisfying constraints that guarantee appropriate operating conditions for the units.

[Source: Frederick S. Hillier and Gerald J. Lieberman. Introduction to Operations Research - 7th ed., 2000, McGraw-Hill, ISBN 0-07-232169-5]

A rebel army is attempting to overthrow the elected government of the Russian Federation. The United States government has decided to assist its ally by quickly sending troops and supplies to the Federation. A plan needs to be developed for shipping the troops and supplies most effectively. Depending on the overall measure of performance, the analysis requires formulating and solving a shortest-path problem, a minimum cost flow problem, or a maximum flow problem.