Search

Conventional neural-network training algorithms often get stuck in local minima. To find the global optimum, training is conventionally repeated with ten, or so, random starting values for the weights. Here we develop an analytical procedure to determine how many times a neural network needs to be trained, with random starting weights, to ensure that the best of those is within a desirable lower percentile of all possible trainings, with a certain level of confidence. The theoretical developments are validated by experimental results. While applied to neural-network training, the method is generally applicable to nonlinear optimization. Index Terms - Neural-network training, steady-state identification, weakest-link-in-a-chain.

The article offers information about the ChE undergraduate enrollment trends and provides analysis, perspective, and advice that will help in industrial recruitment planning and academic program management. It mentions that academic administrators and industry hiring managers should prepare now for the next decline in enrollment.

A new method of in-line control of pH neutralization using fuzzy logic has a wide operational range for handling nonlinear processes, is robust in dealing with random disturbances and possible system parameter drafting, and is relatively easy to operate. pH control is important in semiconductor manufacturing, regulating etching, acid treating and waste water neutralization.

Describes the objectives, assignment structure, requirements, and results of a team project in a junior-level transport course. Provides tables of rules, projects list, and a group member evaluation form. (YP)