Research map / Detection and segmentation / CNN features
Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity
Aria Wang, Michael Tarr, Leila Wehbe
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 3D task features (keypoints, edges) instead of 2D task features | ridge encoding models on Taskonomy latents · BOLD5000 scene-selective ROIs (PPA, RSC, OPA, LOC) | prediction correlation | Improved |
| use 3D task features instead of 2D task features | ridge encoding models on Taskonomy latents · BOLD5000 early visual areas | prediction correlation | No clear effect |
| use hierarchical clustering with ward instead of average linkage for brain-derived task tree (ablation) | Neural Taskonomy task tree · BOLD5000 task similarity tree | cluster structure | No clear effect |
| use euclidean distance instead of cosine similarity for task similarity (ablation) | Neural Taskonomy task similarity · BOLD5000 task similarity | similarity structure | No clear effect |
Closest papers by meaning
- Learning Neural Representations of Human Cognition across Many fMRI Studies (NeurIPS 2017 · similarity 0.89)
- Geometry of naturalistic object representations in recurrent neural network models of working memory (NeurIPS 2024 · similarity 0.88)
- A Convolutional Neural Network Interpretable Framework for Human Ventral Visual Pathway Representation (AAAI 2024 · similarity 0.87)
- SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments (ICLR 2025 · similarity 0.87)
- Transformer brain encoders explain human high-level visual responses (NeurIPS 2025 · similarity 0.87)
- Brain Decodes Deep Nets (CVPR 2024 · similarity 0.87)
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.
