Cluster-Based Input Weight Initialization for Echo State Networks
Research output: Contribution to journal › Research article › Contributed › peer-review
Contributors
Abstract
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.
Details
Original language | English |
---|---|
Number of pages | 12 |
Journal | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 2022 |
Issue number | 34(10) |
Publication status | Published - 2022 |
Peer-reviewed | Yes |
External IDs
Scopus | 85124228195 |
---|---|
ORCID | /0000-0003-0167-8123/work/167214847 |
Keywords
ASJC Scopus subject areas
Keywords
- Clustering, Clustering algorithms, Mathematical models, Neurons, Reservoirs, Self-organizing feature maps, Task analysis, Training, echo state networks (ESNs), reservoir computing, unsupervised pretraining.