Research map / Probabilistic and scientific modeling / Dynamical systems
From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations
Vezha Boboeva, Alberto Pezzotta, George Dimitriadis, Athena Akrami
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies how recurrent neural networks extract abstract relational structure from temporal sequences, linking low-rank recurrent dynamics to schema-like representations.
Problem
How temporal sequences are transformed into abstract relational representations (cognitive schemas) that generalize across specific elements, e.g., recognizing that aab, ccd, and eef share one pattern.
Approach
Attributes abstract relational representation formation to low-rank recurrent dynamics in neural networks trained on sequence tasks; details beyond the abstract are not available.
Closest papers by meaning
- Dynamical phases of short-term memory mechanisms in RNNs (ICML 2025 · similarity 0.90)
- Learning Reveals Invisible Structure in Low-Rank RNNs (NeurIPS 2026 · similarity 0.88)
- How connectivity structure shapes rich and lazy learning in neural circuits (ICLR 2024 · similarity 0.87)
- Learning dynamics in linear recurrent neural networks (ICML 2025 · similarity 0.87)
- Discovering plasticity rules that organize and maintain neural circuits (NeurIPS 2024 · similarity 0.87)
- How are linear representations learned? Exact solutions to the dynamics of abstraction (NeurIPS 2026 · similarity 0.87)
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.
