Research map / Architectures and efficiency / RNNs and normalization
Metamers of neural networks reveal divergence from human perceptual systems
Jenelle Feather, Alex Durango, Ray Gonzalez, Josh McDermott
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 aliasing (hanning pooling instead of max pooling/strided conv) (ablation) | word-trained auditory CNN · human recognition of audio model metamers | human recognition | Improved |
| train the network (versus random initialization) (ablation) | reduced-aliasing auditory CNN · human recognition of audio model metamers | human recognition | Hurt |
| train on AudioSet task instead of word task (ablation) | reduced-aliasing auditory CNN · human recognition of audio model metamers | human recognition | Hurt |
| add AudioSet training on top of word task (ablation) | reduced-aliasing auditory CNN · human recognition of audio model metamers | human recognition | No clear effect |
| generate metamers from deeper layers | image and audio networks · human recognition of metamers | human recognition | Hurt |
Closest papers by meaning
- Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts (NeurIPS 2025 · similarity 0.85)
- Model–Behavior Alignment under Flexible Evaluation: When the Best-Fitting Model Isn’t the Right One (NeurIPS 2025 · similarity 0.85)
- Evaluating alignment between humans and neural network representations in image-based learning tasks (NeurIPS 2024 · similarity 0.84)
- AND: Audio Network Dissection for Interpreting Deep Acoustic Models (ICML 2024 · similarity 0.84)
- Graph Metanetworks for Processing Diverse Neural Architectures (ICLR 2024 · similarity 0.84)
- Geometry of naturalistic object representations in recurrent neural network models of working memory (NeurIPS 2024 · similarity 0.84)
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.
