Research map / Architectures and efficiency / RNNs and normalization
Comparison Against Task Driven Artificial Neural Networks Reveals Functional Properties in Mouse Visual Cortex
Jianghong Shi, Eric Shea-Brown, Michael Buice
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 |
|---|---|---|---|
| reduce number of natural images to about 118 or vary which images are shown (ablation) | SSM/SVCCA VGG16-pseudo-depth · tiny ImageNet VGG16 self-comparison | pseudo-depth stability | No clear effect |
| subsample fewer neurons from the compared representation (ablation) | SSM/SVCCA similarity score · VGG16 self-comparison | similarity score | Hurt |
| subsample about 1000 neurons rather than all (ablation) | VGG16-pseudo-depth · VGG16 self-comparison | pseudo-depth | No clear effect |
| change input image resolution to 32x32 or 128x128 (ablation) | SSM pseudo-depth · Allen Brain Observatory vs VGG16 | pseudo-depth | No clear effect |
| change input image resolution to 32x32 or 128x128 (ablation) | SVCCA pseudo-depth · Allen Brain Observatory vs VGG16 | pseudo-depth | Mixed |
Closest papers by meaning
- Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex (NeurIPS 2021 · similarity 0.93)
- Disentangling the Factors of Convergence between Brains and Computer Vision Models (ICLR 2026 · similarity 0.90)
- Generalized Shape Metrics on Neural Representations (NeurIPS 2021 · similarity 0.90)
- Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli (NeurIPS 2024 · similarity 0.89)
- Brain Decodes Deep Nets (CVPR 2024 · similarity 0.88)
- Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks (ICML 2025 · similarity 0.88)
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.
