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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use a nonlinear decoder instead of a linear decoder | RNN hidden-state decoding of MDFA states · Approximately 500 sampled regular languages | decoding accuracy | No clear effect |
| Decode to an abstraction of MDFA states rather than the exact MDFA states | RNN hidden-state decoding · Regular-language recognition | decoding accuracy | Improved |
| Choose state merges by decoding accuracy instead of merging states randomly | Greedy abstraction algorithm · Approximately 500 sampled regular languages | normalized AUC | Improved |
| Increase the number of states in the MDFA | RNN decoding of MDFA states · Sampled regular languages | decoding accuracy | Hurt |
Closest papers by meaning
- Training Neural Networks as Recognizers of Formal Languages (ICLR 2025 · similarity 0.90)
- M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling (NeurIPS 2026 · similarity 0.86)
- Separations in the Representational Capabilities of Transformers and Recurrent Architectures (NeurIPS 2024 · similarity 0.86)
- Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models (ICML 2025 · similarity 0.86)
- Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures (ICLR 2025 · similarity 0.86)
- Neural-Symbolic Recursive Machine for Systematic Generalization (ICLR 2024 · similarity 0.86)
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.
