How Many Bits Does it Take to Quantize Your Neural Network?

DOI10.1007/978-3-030-45237-7_5zbMath1483.68192OpenAlexW2946149952MaRDI QIDQ5164169

Mathias Lechner, Mirco Giacobbe, Thomas A. Henzinger

Publication date: 10 November 2021

Published in: Tools and Algorithms for the Construction and Analysis of Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-45237-7_5

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Specification and verification (program logics, model checking, etc.) (68Q60) Networks and circuits as models of computation; circuit complexity (68Q06)

Related Items (4)

\textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks ⋮ Bit-precise verification of discontinuity errors under fixed-point arithmetic ⋮ An SMT-based approach for verifying binarized neural networks ⋮ An SMT theory of fixed-point arithmetic

Cites Work

• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Challenging SMT solvers to verify neural networks
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks

This page was built for publication: How Many Bits Does it Take to Quantize Your Neural Network?