Incremental stacked width learning system with depth structure

• Main Authors: CHEN JUNLONG, JIA XUE, YE HANYUN, FENG QIYING, ZHANG TONG, LIU ZHULIN
• Format: Patent
• Language: Chinese; English
• Published: 16.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides an incremental stacked width learning system with a deep structure. The incremental stacked width learning system is characterized by comprising n width learning system modules,the n width learning system modules are connected and stacked through residual errors; wherein the output of the i1th width learning system module is used as the input of the ith width learning system module, the expected output of the ith width learning system module is the residual error of the first-i1th width learning system module, and i is less than or equal to n; and the final output of the system is the output sum of the n width learning system modules. The system keeps the advantages of high efficiency and quickness of a width learning system, and meanwhile, a plurality of width learning system modules are connected and stacked through residual errors, so that the depth of the network is increased, and the network has strong learning capability. 本发明提供了一种具有深度结构的增量堆叠式宽度学习系统，其特征在于：包括n个宽度学习系统模块；n个宽度学习系统模块通过残