Fading memory echo state networks are universal.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 33611064.
- Also identified by DOI 10.1016/j.neunet.2021.01.025.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Echo state networks (ESNs) have been recently proved to be universal approximants for input/output systems with respect to various L<sup>p</sup>-type criteria. When 1≤p<∞, only p-integrability hypotheses need to be imposed, while in the case p=∞ a uniform boundedness hypotheses on the inputs is required. This note shows that, in the last case, a universal family of ESNs can be constructed that contains exclusively elements that have the echo state and the fading memory properties. This conclusion could not be drawn with the results and methods available so far in the literature.
Medical subject headings
- Neural Networks, Computer