Verifying generalization in deep learning

DOI10.1007/978-3-031-37703-7_21zbMATH Open1545.68067MaRDI QIDQ6535549FDOQ6535549

Authors: Guy Amir, Osher Maayan, Tom Zelazny, Guy Katz, Michael Schapira 

Publication date: 12 January 2024

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Specification and verification (program logics, model checking, etc.) (68Q60)

Cites Work

• Deep learning
• Verifying Recurrent Neural Networks Using Invariant Inference
• Reinforcement learning. An introduction
• Title not available (Why is that?)
• Natural language processing (almost) from scratch
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• An SMT-based approach for verifying binarized neural networks
• Formal verification of piece-wise linear feed-forward neural networks
• Formal verification of neural network controlled autonomous systems
• Reachability analysis for neural feedback systems using regressive polynomial rule inference
• DeepSafe: a data-driven approach for assessing robustness of neural networks
• Formal specification for deep neural networks
• Run-time optimization for learned controllers through quantitative games
• Neural network repair with reachability analysis
• Static analysis of ReLU neural networks with tropical polyhedra
• Bisimulations for neural network reduction
• Reluplex: a calculus for reasoning about deep neural networks
• Probabilistic Horn clause verification
• Efficient neural network analysis with sum-of-infeasibilities

Cited In (1)

• Verifying the generalization of deep learning to out-of-distribution domains

This page was built for publication: Verifying generalization in deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535549)