Pith. sign in

REVIEW

Cluster-based Input Weight Initialization for Echo State Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.04710 v3 pith:FR5UXH4E submitted 2021-03-08 cs.LG cs.AIcs.NE

classification cs.LGcs.AIcs.NE
keywords initializationesnsinputnetworksconnectionsdataechorandomly
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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 whilst 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.

Discussion (0). Continue with ORCID to comment.

Pith tools