Research map / Probabilistic and scientific modeling / Dynamical systems
Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics
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 |
|---|---|---|---|
| add intrinsic plasticity (learned per-class excitability lambda) to the network (ablation) | PPG Hebbian network · MNIST digits 0-3, 0.5% and 5% labels | classification success rate | Helped |
| vary number of labels (0.5% vs 5%) and iterations over the dataset | network with IP · MNIST digits 0-3 | classification success rate | No clear effect |
| learn class-specific intensities instead of ad hoc intensity normalization | PPG network · Shiny vs dull spheres | class separation by intensity: 620 -> 720 | Helped |
| use full MNIST instead of digits 0-3 | PPG network · MNIST | qualitative results | No clear effect |
| run neural dynamics instead of exact EM | PPG model · Artificial rectangles data | parameter recovery | No clear effect |
Closest papers by meaning
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.89)
- Impression learning: Online representation learning with synaptic plasticity (NeurIPS 2021 · similarity 0.89)
- Learning efficient task-dependent representations with synaptic plasticity (NeurIPS 2020 · similarity 0.88)
- Model Based Inference of Synaptic Plasticity Rules (NeurIPS 2024 · similarity 0.87)
- Discovering plasticity rules that organize and maintain neural circuits (NeurIPS 2024 · similarity 0.86)
- Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning (ICLR 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.
