Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures With Gradient Learnings.
Where this comes from
- Record sourced from PubMed, PMID 34780334.
- Also identified by DOI 10.1109/TNNLS.2021.3123533.
- 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
This letter summarizes and proves the concept of bounded-input bounded-state (BIBS) stability for weight convergence of a broad family of in-parameter-linear nonlinear neural architectures (IPLNAs) as it generally applies to a broad family of incremental gradient learning algorithms. A practical BIBS convergence condition results from the derived proofs for every individual learning point or batches for real-time applications.