Research map / Probabilistic and scientific modeling / Dynamical systems
Impression learning: Online representation learning with synaptic plasticity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace NVI* three-factor update with impression learning update | Impression learning · Artificial stimulus task | gradient SNR | Helped |
| Replace NVI* with impression learning as stimulus dimension grows | Impression learning · Artificial stimuli, varying dimensionality | asymptotic negative ELBO | Helped |
| Impression learning versus backpropagation | Impression learning · Artificial stimuli, varying dimensionality | asymptotic negative ELBO | No clear effect |
| Lengthen phase duration K from 2 to 32 (ablation) | Impression learning · Artificial stimuli | negative ELBO loss | No clear effect |
| Lengthen phase duration K from 2 to 32 (ablation) | Impression learning · Artificial stimuli | correlation with pure inference-mode activity | Hurt |
| Lengthen inference phase while keeping short generative bursts (ablation) | Impression learning · Artificial stimuli | perceptual disturbance and learning time | Mixed |
| Use impression learning instead of NVI* in two-layer network | Impression learning · Free Spoken Digits Dataset | test loss | Helped |
Closest papers by meaning
- Learning efficient task-dependent representations with synaptic plasticity (NeurIPS 2020 · similarity 0.91)
- Model Based Inference of Synaptic Plasticity Rules (NeurIPS 2024 · similarity 0.90)
- Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities (ICLR 2024 · similarity 0.90)
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.89)
- Normative Networks for Source Separation via Local Plasticity and Dendritic Computation (NeurIPS 2026 · similarity 0.88)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · 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.