Research map / Probabilistic and scientific modeling / Dynamical systems
Translation-equivariant Representation in Recurrent Networks with a Continuous Manifold of Attractors
Wenhao Zhang, Ying Nian Wu, Si Wu
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 |
|---|---|---|---|
| add derivative-of-recurrent-weight component (dxWr) to CAN connections | Continuous attractor network · Simulated 1D ring network | translation of bump along manifold | Improved |
| add speed neuron populations with shifted feedback connections to the CAN | Drosophila-inspired three-population circuit · Simulated network | speed-proportional bump translation | Improved |
| vary order of two constant speeds v1 then v2 versus v2 then v1 | Modified CAN · Path integration simulation | integrated translation distance | No clear effect |
| replace multiplicative synaptic modulation by multiplicative gain on speed neurons | Speed-neuron circuit · Simulated joint tuning | stimulus tuning width invariance to speed | Improved |
| perturb CAN state away from the Gaussian attractor profile | CAN · Stability analysis | eigenvalues of perturbation: lambda1 = 1 | No clear effect |
Closest papers by meaning
- Flow Equivariant Recurrent Neural Networks (NeurIPS 2025 · similarity 0.88)
- Shaping the distribution of neural responses with interneurons in a recurrent circuit model (NeurIPS 2024 · similarity 0.86)
- The Bayesian sampling in a canonical recurrent circuit with a diversity of inhibitory interneurons (NeurIPS 2024 · similarity 0.86)
- Neurons as Detectors of Coherent Sets in Sensory Dynamics (NeurIPS 2025 · similarity 0.86)
- Unconditional stability of a recurrent neural circuit implementing divisive normalization (NeurIPS 2024 · similarity 0.85)
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models (NeurIPS 2025 · similarity 0.85)
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.
