20 citations · 25 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction
Jan Glaser, Ivo Bukovsky, Marcel Jirina
This paper extends the concept of Learning Entropy (LE) from temporal adaptive systems to spatial learning in multilayer perceptron networks (MLPs) applied to image data. Instead o…
cs.LG2021★ 5 cited
A Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures with Gradient Learnings
Ivo Bukovsky, Gejza Dohnal, Peter M. Benes +2
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 archi…