.png){kind=icon}
返回
Cluster-Based Input Weight Initialization for Echo State Networks
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2022.3145565.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Echo state networks (ESNs) are a special type of recurrent neural networks (RNNs), in which the input and recurrent connections are traditionally generated randomly, and only the output weights are trained. Despite the recent success of ESNs in various tasks of audio, image, and radar recognition, we postulate that a purely random initialization is not the ideal way of initializing ESNs. The aim of this work is to propose an unsupervised initialization of the input connections using the K-means algorithm on the training data. We show that for a large variety of datasets, this initialization performs equivalently or superior than a randomly initialized ESN while needing significantly less reservoir neurons. Furthermore, we discuss that this approach provides the opportunity to estimate a suitable size of the reservoir based on prior knowledge about the data.
Keyword:
Reservoirs
Neurons
Clustering algorithms
Task analysis
Self-organizing feature maps
Training
Mathematical models
Clustering
echo state networks (ESNs)
reservoir computing
unsupervised pretraining
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏Information processing using a single dynamical node as complex system使用单个动态节点作为复杂系统的信息处理.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏分享收藏A Comparative Study of Bituminous Mixtures with Recycled Polyethylene Added by Dry and Wet Processes
PREAI
分享收藏
查看更多内容