Research map / Probabilistic and scientific modeling / Dynamical systems
Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System
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 |
|---|---|---|---|
| Integrate temporal information per whisker before spatially combining whisker features | Temporal-Spatial model · ShapeNet 117-class shape recognition | top-1 accuracy: 15.2% | Helped |
| Combine information from 12 sweeps rather than 3 (ablation) | S_more · ShapeNet 117-class shape recognition | top-1 accuracy: 0.20 | Helped |
| Combine information from 12 sweeps rather than 3 (ablation) | S_more · ShapeNet 117-class shape recognition | top-5 accuracy: 0.53 | Helped |
| Use trained filters instead of random filters (ablation) | DNNs across the tested architecture families · ShapeNet 117-class shape recognition | accuracy | Helped |
| Use at least four layers rather than a shallower architecture (ablation) | DNNs across the tested architecture families · ShapeNet 117-class shape recognition | accuracy | Helped |
| Add long-range feedback connections (ablation) | Recurrent networks · ShapeNet 117-class shape recognition | accuracy | Helped |
| Replace long-range feedback with purely local recurrent connections (ablation) | Recurrent networks · ShapeNet 117-class shape recognition | accuracy | Hurt |
| Increase parameter count within an architectural family (ablation) | DNNs · ShapeNet 117-class shape recognition | accuracy | Mixed |
| Use a Temporal-Spatial architecture rather than other architectural families | DNNs with comparable parameter counts · ShapeNet 117-class shape recognition | accuracy | Helped |
Closest papers by meaning
- Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain (NeurIPS 2025 · similarity 0.87)
- Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets (NeurIPS 2025 · similarity 0.84)
- Neural Encoding and Decoding at Scale (ICML 2025 · similarity 0.84)
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data (ICLR 2024 · similarity 0.84)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · similarity 0.83)
- Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos (NeurIPS 2024 · similarity 0.83)
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.