提出了一种基于最小分类错误(MCE)训练的采用多层感知器(MLP)结构的模式分类器设计方法。
An improved design method on pattern classifier based on multi-layer perceptrons (MLP) by means of minimum classification error (MCE) training was proposed.
建筑大多数是低矮的多层结构,低矮的体量使掘土量减少到最小。
The buildings are mostly short multistory structures, squat volumes with minimal excavation needed.
另外,由于电池内的温度梯度的最小化,所述多层结构也 不太可能变形和破裂。
The multilayer structure is also unlikely to distort and fracture by minimizing the temperature gradient in the cell.
应用推荐