Verifying binarized neural networks by Angluin-style learning
From MaRDI portal
Publication:2181945
DOI10.1007/978-3-030-24258-9_25zbMath1441.68214OpenAlexW2955171822MaRDI QIDQ2181945
Arthur Choi, Adnan Darwiche, Andy Shih
Publication date: 20 May 2020
Full work available at URL: https://doi.org/10.1007/978-3-030-24258-9_25
Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)
Related Items
\textsf{BDD4BNN}: a BDD-based quantitative analysis framework for binarized neural networks, Exploiting verified neural networks via floating point numerical error, Learning finite state models from recurrent neural networks, On the (complete) reasons behind decisions, Quantitative Verification for Neural Networks using ProbStars
Uses Software