Research map / Probabilistic and scientific modeling / Dynamical systems
A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation
Junfeng Zuo, Xiao Liu, Ying Nian Wu, Si Wu, Wenhao Zhang
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 |
|---|---|---|---|
| apply a time-invariant control input with gain alpha to the continuous attractor network | Recurrent CAN circuit · Network simulation | neural sequence time scale | Improved |
| use a negative control input gain (alpha < 0) | Recurrent CAN circuit · Network simulation | time-reversed neural sequence | Improved |
| change input gain across sequences of the same polarity vs different polarities | Single neuron responses · Network simulation | overlap of single-neuron temporal responses after rescaling | Mixed |
| add multiplicative (Poisson-like) noise to the recurrent circuit | Recurrent CAN circuit · Network simulation | std of sequence duration vs mean (Weber's law) | Improved |
| increase control input gain | Recurrent CAN circuit with multiplicative noise · Network simulation | mean sequence duration | Improved |
| vary control input gain at test time after training feedforward circuit at one temporal scale | Recurrent circuit plus 3-layer perceptron · Handwritten digit 6 sequence | generalization across temporal scales | Improved |
| use negative gain for the handwritten sequence generator | Recurrent circuit plus 3-layer perceptron · Handwritten digit 6 sequence | reversed-order sequence generation | Improved |
| switch to a different digit pattern without retraining the feedforward circuit | Disentangled circuit · Handwritten digits | pattern generation | Hurt |
Closest papers by meaning
- Dynamical phases of short-term memory mechanisms in RNNs (ICML 2025 · similarity 0.87)
- Unconditional stability of a recurrent neural circuit implementing divisive normalization (NeurIPS 2024 · similarity 0.86)
- Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons (NeurIPS 2026 · similarity 0.85)
- Deep Reinforcement Learning with Time-Scale Invariant Memory (AAAI 2025 · similarity 0.85)
- Inference of Neural Dynamics Using Switching Recurrent Neural Networks (NeurIPS 2024 · similarity 0.85)
- From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination (NeurIPS 2026 · 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.
