A Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures with Gradient Learnings

11/25/2021

∙

by   Ivo Bukovsky, et al.

∙

0

∙

share

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 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.