Towards global neural network abstractions with locally-exact reconstruction

DOI10.1016/J.NEUNET.2023.06.002MaRDI QIDQ6488831

Lucas C. Cordeiro, Edoardo Manino, Iury Bessa

Publication date: 26 October 2023

Published in: Neural Networks (Search for Journal in Brave)

zbMATH Keywords

neural networksabstract interpretationglobal abstraction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Multilayer feedforward networks are universal approximators
• Lossless compression of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• An abstraction-based framework for neural network verification
• Error bounds for approximations with deep ReLU networks
• Neural network with unbounded activation functions is universal approximator
• Sparse Polynomial Zonotopes: A Novel Set Representation for Reachability Analysis
• Abstract Interpretation Frameworks

This page was built for publication: Towards global neural network abstractions with locally-exact reconstruction