Parameter identifiability of a deep feedforward ReLU neural network

DOI10.1007/s10994-023-06355-4zbMath1528.68353arXiv2112.12982OpenAlexW4200634384MaRDI QIDQ6188062

François Bachoc, Joachim Bona-Pellissier, François Malgouyres

Publication date: 11 January 2024

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.12982

zbMATH Keywords

symmetriesparameter recoverydeep learningReLU networksequivalent parameters

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Unnamed Item
• Reconstructing a neural net from its output
• Topological properties of the set of functions generated by neural networks of fixed size
• Protect privacy of deep classification networks by exploiting their generative power
• TRU-NET: a deep learning approach to high resolution prediction of rainfall
• Deep learning and multivariate time series for cheat detection in video games
• Cryptanalytic extraction of neural network models
• Lossless compression of deep neural networks
• An embedding of ReLU networks and an analysis of their identifiability
• Multilinear Compressive Sensing and an Application to Convolutional Linear Networks
• Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy

This page was built for publication: Parameter identifiability of a deep feedforward ReLU neural network