The complexity of explaining neural networks through (group) invariants

zbMATH Open1403.68186MaRDI QIDQ4645652FDOQ4645652

Authors: Danielle Ensign, Scott Neville, Arnab Paul, Suresh Venkatasubramanian 

Publication date: 10 January 2019

Full work available at URL: http://proceedings.mlr.press/v76/ensign17a.html

Recommendations

• The complexity of explaining neural networks through (group) invariants
• Probabilistic symmetries and invariant neural networks
• Representation theory and invariant neural networks
• A unifying framework for invariant pattern recognition
• Analysis of deep convolutional networks from group theory viewpoint

zbMATH Keywords

neural networksNP-completenessgroup theory

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Cited In (3)

• The complexity of explaining neural networks through (group) invariants
• Challenges in Markov chain Monte Carlo for Bayesian neural networks
• Probabilistic symmetries and invariant neural networks

This page was built for publication: The complexity of explaining neural networks through (group) invariants

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4645652)