Research map / Architectures and efficiency / RNNs and normalization
Dimensionality Mismatch Between Brains and Artificial Neural Networks
Santiago Galella, Maren Wehrheim, Matthias Kaschube
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Quantifies and compares the linear and non-linear dimensionality of human fMRI responses and artificial neural network representations during natural vision across hierarchical processing stages.
Problem
Unclear how the representational geometry (dimensionality) of hierarchical biological and artificial vision systems evolves across processing stages, and what functional consequences differences may have.
Approach
Systematically measures both linear and non-linear dimensionality of human fMRI activity and ANN activations during natural image viewing and compares them stage by stage to reveal dimensionality mismatches between brains and networks.
Experimental setup
Metrics: linear dimensionality non-linear dimensionality
Closest papers by meaning
- Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts (NeurIPS 2025 · similarity 0.88)
- Evaluating alignment between humans and neural network representations in image-based learning tasks (NeurIPS 2024 · similarity 0.88)
- Geometry of naturalistic object representations in recurrent neural network models of working memory (NeurIPS 2024 · similarity 0.88)
- Characterizing Universal Object Representations Across Vision Models (NeurIPS 2026 · similarity 0.87)
- Brain Decodes Deep Nets (CVPR 2024 · similarity 0.87)
- A Convolutional Neural Network Interpretable Framework for Human Ventral Visual Pathway Representation (AAAI 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.
