Paper ID: 2111.12877

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

Ivo Bukovsky, Gejza Dohnal, Peter M. Benes, Kei Ichiji, Noriyasu Homma

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.

Submitted: Nov 25, 2021