Research map / Probabilistic and scientific modeling / Dynamical systems
Synaptic plasticity learning rules
Explains learning via burst-dependent plasticity, interneurons, and feedback in recurrent neural circuits.
72 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Dynamical systems, keyword cluster “brain · activity · neurons”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
19 papers in 2023–24 and 25 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 8.4% to 6.5%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · A forward model at Purkinje cell synapses facilitates cerebellar anticipatory control (NeurIPS 2016 · 13 citations)
- 2017 · Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell Responses (ICLR 2017 · 66 citations)
- 2018 · Emergence of grid-like representations by training recurrent neural networks to perform spatial localization (ICLR 2018 · 203 citations)
- 2019 · A unified theory for the origin of grid cells through the lens of pattern formation (NeurIPS 2019 · 48 citations)
- 2020 · Learning Nanoscale Motion Patterns of Vesicles in Living Cells (CVPR 2020 · 9 citations)
- 2021 · Online Learning Of Neural Computations From Sparse Temporal Feedback (NeurIPS 2021 · 0 citations)
- 2022 · Efficient coding, channel capacity, and the emergence of retinal mosaics (NeurIPS 2022 · 15 citations)
- 2023 · Meta-learning families of plasticity rules in recurrent spiking networks using simulation-based inference (NeurIPS 2023 · 2 citations)
- 2024 · Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification (AAAI 2024 · 12 citations)
- 2025 · REMI: Reconstructing Episodic Memory During Internally Driven Path Planning (NeurIPS 2025 · 3 citations)
- 2026 · From movement to cognitive maps: recurrent neural networks reveal how locomotor development shapes hippocampal spatial coding (ICLR 2026 · 1 citation)
Earliest papers here
- A forward model at Purkinje cell synapses facilitates cerebellar anticipatory control (NeurIPS 2016 · 13 citations)
- Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell Responses (ICLR 2017 · 66 citations)
- Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System (NeurIPS 2017 · 15 citations)
What has been tried
48 papers here report 401 measured changes (a component added, removed or swapped, compared with a baseline): helped 59%, no clear effect 13%, hurt 22%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| replace feature concatenation with max pooling | HemiBrain · accuracy | 0.9169 -> 0.9149 | No clear effect | Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification (AAAI 2024 · 12 citations) |
| Increase episodic memory segment duration | Single-room place-field emergence · Number of place cells | Hurt | Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences (NeurIPS 2024 · 8 citations) | |
| Use 4 astrocytes instead of 2 | CIFAR10 · accuracy | 96.70 -> 96.81 | Helped | MA-Net: Rethinking Neural Unit in the Light of Astrocytes (AAAI 2024 · 7 citations) |
| Increase masking ratio | Sensory-cue recall · GC location decoding accuracy | Helped | REMI: Reconstructing Episodic Memory During Internally Driven Path Planning (NeurIPS 2025 · 3 citations) | |
| Increase firing-field width | 1D and 2D environments · context discrimination | Helped | Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes (NeurIPS 2024 · 1 citation) | |
| Use SPINT with context-dependent positional embeddings instead of fixed positional embeddings | M1, M2, and H1 cross-session · R² | Helped | SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding (NeurIPS 2025 · 0 citations) | |
| Add lateral inhibition | Gaussian noise, low- and medium-noise odor discrimination · accuracy | 6.80% when N.I. = 0.0; 18.52% when N.I. = 0.1 | Helped | Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies (NeurIPS 2025 · 0 citations) |
| Remove the projection operator | CLEVR-Tex · FG-ARI | 80.5\spm{1.5} -> 79.0\spm{2.5} | No clear effect | Artificial Kuramoto Oscillatory Neurons (ICLR 2025 · 0 citations) |
| enable GPU | Speed benchmark · runtime | a factor of six | Helped | convSeq: Fast and Scalable Method for Detecting Patterns in Spike Data (ICML 2024 · 0 citations) |
| Generate soma branches with an unconditional VAE instead of directly providing them | VPM, RGC, M1-EXC, M1-INH · Morphological statistics (six metrics) | Mixed | MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation (ICML 2024 · 0 citations) | |
| Use a nonlinear activation function in the first layer | U(1) operator search · rotation speed computation | Helped | The motion planning neural circuit in goal-directed navigation as Lie group operator search (NeurIPS 2024 · 0 citations) | |
| Add momentum stopping when the gradient changes sign | Handwritten digit recognition · error | 0.1662 -> 0.0699 | Helped | realSEUDO for real-time calcium imaging analysis (NeurIPS 2024 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 19 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- CIFAR-10 · 2 of 19 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 44 papers; from OpenAlex and the papers' affiliations).
- University of Pennsylvania · 4 papers
- University of Washington · 4 papers
- Flatiron Institute · 3 papers
- Simons Foundation · 3 papers
- New York University · 3 papers
- University of California, Los Angeles · 3 papers
- Peking University · 3 papers
- Tsinghua University · 3 papers
- Harvard University · 2 papers
- University of Tuebingen · 2 papers
Use it
Download BibTeX of 37 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Latent models of neural activity (70 papers)
- Recurrent circuit models of inference (70 papers)
- Low-rank and diffusion neural dynamics (53 papers)
- Functional connectivity modeling (50 papers)
Elsewhere in the topic
- Physics-informed dynamics learning (127 papers)
- Latent dynamics models (111 papers)
- State-space inference for stochastic systems (104 papers)
- Switching and law-discovery dynamics (81 papers)
- Latent-space control and planning (78 papers)
- Data assimilation from sparse observations (58 papers)
- Stochastic population dynamics (53 papers)
- Stable contractive dynamics (42 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).