مقاله رشد شبکه حالت اکو با منابع فرعی چندگانه

عنوان مقاله فارسی: رشد شبکه حالت اکو با منابع فرعی چندگانه عنوان مقاله لاتین: Growing Echo-State Network With Multiple Subreservoirs نویسندگان: Junfei Qiao; Fanjun Li; Honggui Han; Wenjing Li تعداد صفحات: 15 سال انتشار: 2017 زبان: لاتین Abstract: An echo-state network (ESN) is an effective alternative to gradient methods for training recurrent neural network. However, it is difficult to determine the structure (mainly the reservoir) of the ESN to match with the given application. In this paper, a growing ESN (GESN) is proposed to design the size and topology of the reservoir automatically. First, the GESN makes use of the block matrix theory to add hidden units to the existing reservoir group by group, which leads to