Research map / Label-efficient and robust learning / Self-supervised and contrastive
Learning Time-Invariant Representations for Individual Neurons from Population Dynamics
Lu Mi, Trung Le, Tianxing He, Eli Shlizerman, Uygar Sümbül
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 permutation-invariant population summary inputs (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.512 -> 0.756 | Improved |
| add running speed input (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.512 -> 0.609 | Improved |
| add pupil size input (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.609 -> 0.658 | Improved |
| add frame state input (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.658 -> 0.683 | Improved |
| add population activity input (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.683 -> 0.732 | Improved |
| add center-surround activity input (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.732 -> 0.756 | Improved |
| add population inputs (ablation) | NeuPRINT · Class prediction (MLP) | top-1 accuracy: 0.752 -> 0.807 | No clear effect |
| replace linear dynamics model with transformer (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.512 -> 0.756 | Improved |
| replace RNN dynamics model with transformer (ablation) | NeuPRINT · Subclass prediction (MLP) | top-1 accuracy: 0.610 -> 0.756 | Improved |
| use MSE instead of Gaussian NLL objective (ablation) | NeuPRINT transformer · Subclass prediction (MLP) | top-1 accuracy: 0.707 -> 0.756 | Improved |
| use MSE instead of Gaussian NLL objective (ablation) | NeuPRINT nonlinear model · Subclass prediction (MLP) | top-1 accuracy: 0.537 -> 0.512 | Mixed |
| self-supervised NeuPRINT instead of supervised LOLCAT | NeuPRINT · Subclass prediction single mouse | top-1 accuracy: 0.404 -> 0.537 | Improved |
Closest papers by meaning
- Know Thyself by Knowing Others: Learning Neuron Identity from Population Context (NeurIPS 2025 · similarity 0.89)
- Neuron Platonic Intrinsic Representation From Dynamics Using Contrastive Learning (ICLR 2025 · similarity 0.88)
- BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation (ICLR 2025 · similarity 0.87)
- Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution (NeurIPS 2024 · similarity 0.87)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · similarity 0.86)
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data (ICLR 2024 · similarity 0.86)
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.
