Research map / Probabilistic and scientific modeling / Dynamical systems
Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes
Gehua Ma, Runhao Jiang, Rui Yan, Huajin Tang
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 |
|---|---|---|---|
| Use temporal conditioning rather than an isotropic Gaussian prior (ablation) | TeCoS-LVM · Four retinal datasets | model performance | Improved |
| Use Noisy LIF neurons to introduce neuron-level stochasticity | TeCoS-LVM · Four retinal datasets | firing-rate correlation | Improved |
| Use Noisy LIF neurons instead of deterministic LIF neurons | TeCoS-LVM · Spike train distances | spike train distance | Mixed |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM · Movie 1 Retina 1 | Pearson correlation coefficient: 0.254 -> 0.579 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM · Movie 1 Retina 1 | Spike train dissimilarity: 850.418 -> 371.057 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM Noisy · Movie 1 Retina 1 | Pearson correlation coefficient: 0.653 -> 0.728 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM Noisy · Movie 1 Retina 1 | Spike train dissimilarity: 370.099 -> 354.989 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM · Movie 2 Retina 2 | Pearson correlation coefficient: 0.471 -> 0.616 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM · Movie 2 Retina 2 | Spike train dissimilarity: 1273.267 -> 1003.489 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM Noisy · Movie 2 Retina 2 | Pearson correlation coefficient: 0.748 -> 0.822 | Improved |
| Replace LIF-Rate hidden neurons with spiking hidden neurons (ablation) | TeCoS-LVM Noisy · Movie 2 Retina 2 | Spike train dissimilarity: 1078.830 -> 1021.384 | Improved |
| Train on short sequences and evaluate on longer sequences | TeCoS-LVM · Longer test sequences | firing-rate correlation | Hurt |
Closest papers by meaning
- Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks (NeurIPS 2023 · similarity 0.87)
- Training High Performance Spiking Neural Network by Temporal Model Calibration (ICML 2025 · similarity 0.86)
- Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity (NeurIPS 2025 · similarity 0.86)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · similarity 0.86)
- Spike Distance Function as a Learning Objective for Spike Prediction (ICML 2024 · similarity 0.86)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · 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.
