Topological properties of basins of attraction of width bounded autoencoders

DOI10.1142/s0219530524500076MaRDI QIDQ6587591

Hans-Peter Beise, Steve Dias Da Cruz

Publication date: 14 August 2024

Published in: Analysis and Applications (Singapore) (Search for Journal in Brave)

zbMATH Keywords

autoencoderbasin of attractiondynamical systemneural network approximationbounded width neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stability of topological dynamical systems (37B25) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Unnamed Item
• Unnamed Item
• On a model of associative memory with huge storage capacity
• A simple neural network generating an interactive memory
• The capacity of the Hopfield associative memory
• Overparameterized neural networks implement associative memory
• On Transversality of Bent Hyperplane Arrangements and the Topological Expressiveness of ReLU Neural Networks
• Reconciling modern machine-learning practice and the classical bias–variance trade-off
• Neural networks and physical systems with emergent collective computational abilities.
• Correlation Matrix Memories
• On decision regions of narrow deep neural networks

This page was built for publication: Topological properties of basins of attraction of width bounded autoencoders