AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks

Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Richard G. Baraniuk, Swarat Chaudhuri, Ankit B. Patel

ICLR 2019 · Architectures and efficiency › RNNs and normalization · approach: RNN training dynamics and gradients · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a nonlinear decoder instead of a linear decoderRNN hidden-state decoding of MDFA states · Approximately 500 sampled regular languagesdecoding accuracyNo clear effect
Decode to an abstraction of MDFA states rather than the exact MDFA statesRNN hidden-state decoding · Regular-language recognitiondecoding accuracyImproved
Choose state merges by decoding accuracy instead of merging states randomlyGreedy abstraction algorithm · Approximately 500 sampled regular languagesnormalized AUCImproved
Increase the number of states in the MDFARNN decoding of MDFA states · Sampled regular languagesdecoding accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy