3 papers
cs.LG2020
Distillation of Weighted Automata from Recurrent Neural Networks using a Spectral Approach
Remi Eyraud, Stephane Ayache
This paper is an attempt to bridge the gap between deep learning and grammatical inference. Indeed, it provides an algorithm to extract a (stochastic) formal language from any recu…
cs.FL2019
Learning with Partially Ordered Representations
Jane Chandlee, Remi Eyraud, Jeffrey Heinz +2
This paper examines the characterization and learning of grammars defined with enriched representational models. Model-theoretic approaches to formal language theory traditionally…
cs.LG2018
Explaining Black Boxes on Sequential Data using Weighted Automata
Stephane Ayache, Remi Eyraud, Noe Goudian
Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of lear…