Mon 17 Jan 2022 14:00 - 14:30 at Salon I - Formal Methods in Machine Learning Chair(s): Rupak Majumdar

We present a notion of bisimulation that induces a reduced network which is semantically equivalent to the given neural network. We provide a minimization algorithm to construct the smallest bisimu- lation equivalent network. Reductions that construct bisimulation equiv- alent neural networks are limited in the scale of reduction. We present an approximate notion of bisimulation that provides semantic closeness, rather than, semantic equivalence, and quantify semantic deviation be- tween the neural networks that are approximately bisimilar. The latter provides a trade-off between the amount of reduction and deviations in the semantics.

Mon 17 Jan

Displayed time zone: Eastern Time (US & Canada) change

13:30 - 14:30
Formal Methods in Machine LearningVMCAI at Salon I
Chair(s): Rupak Majumdar MPI-SWS
13:30
30m
Paper
Fanoos: Multi-Resolution, Multi-Strength, Interactive Explanations for Learned SystemsRemote
VMCAI
David Bayani Carnegie Mellon University's School of Computer Science, Stefan Mitsch Carnegie Mellon University, USA
14:00
30m
Paper
Bisimulations for Neural Network ReductionInPerson
VMCAI
Pavithra Prabhakar Kansas State University