.png){kind=icon}
返回
Growing evolutional deep echo state network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.128676.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep echo state network (Deep ESN) is a powerful method for time-series prediction, but developing the optimal structure of Deep ESN remains challenging. A novel generative framework, growing evolutional Deep ESN (GE Deep ESN) is proposed, where networks are generated through alternating growth and evolution. A model compression method is implemented during the evolution phase to optimize the inner structure of the reservoirs, and to automatically determine reservoir size. A simple termination criterion of growth is introduced to determine network depth. The feasibility and superiority of GE Deep ESN were validated experimentally with two benchmark prediction tasks. For real-time trajectory prediction in photoelectric tracking systems, an iterative learning model based on GE Deep ESN is proposed, the real time prediction result showed that network evolution enhances the model's suitability for this task, and improves prediction precision.
Keyword:
Deep echo state network
Reservoir computing
Network sparsification
Time series forecast
Real-time trajectory prediction
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Bimodal distributions of seedling weight in relation to density of Festuca paradoxa Desv..png)
Nature
NatureIF0
PREAI
分享收藏INHIBITION OF HYDROXYAPATITE CRYSTAL GROWTH BY PHOSPHONATED HYDROXY CARBOXYLIC ACIDS, NON-PHOSPHONATED HYDROXY CARBOXYLIC ACIDS, AND POLY (ACRYLIC ACID)磷酸化羟基羧酸、非磷酸化羟基羧酸及聚（丙烯酸）对羟基磷灰石晶体生长的抑制作用
OAAI
OAAI分享收藏
分享收藏Serum biochemical evaluation of healing of critical-sized long bone defects in rats treated with biphasic hydroxyapatite (HA) and β-tricalcium phosphate (β-TCP) bioceramic scaffolds大鼠经双相羟基磷灰石（HA）和β-磷酸三钙（β-TCP）生物陶瓷支架治疗后，大段骨缺损愈合情况的血清生化评价OAAI
OAAI分享收藏
查看更多内容