Bisimulations for Neural Network Reduction
Machine Learning
2021-11-17 v2 Formal Languages and Automata Theory
Abstract
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 bisimulation equivalent network. Reductions that construct bisimulation equivalent 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 between the neural networks that are approximately bisimilar. The latter provides a trade-off between the amount of reduction and deviations in the semantics.
Cite
@article{arxiv.2110.03726,
title = {Bisimulations for Neural Network Reduction},
author = {Pavithra Prabhakar},
journal= {arXiv preprint arXiv:2110.03726},
year = {2021}
}