ArticlePLoS computational biology2024
High-performing neural network models of visual cortex benefit from high latent dimensionality.
Article in PLoS computational biology, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 22 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
22 citing papers in PubMed.
- A single computational objective can produce specialization of streams in visual cortex.Nature communications · 2026Article
- The curriculum effect in visual learning: The role of readout dimensionality.PLoS computational biology · 2026Article
- Tracing aesthetic experience from perception and conception to appraisal using deep convolutional neural networks.iScience · 2026Article
- Category selectivity observed in the human brain is distinct from category selectivity observed in artificial neural networks.bioRxiv : the preprint server for biology · 2026Article
- Exploring neural manifolds across a wide range of intrinsic dimensions.PLoS computational biology · 2026Article
- Foundation models for X-ray interpretation: a narrative review of current techniques and future perspectives in diagnostic imaging.Quantitative imaging in medicine and surgery · 2026Review
- Structured interconnectivity optimizes neural geometry for balancing specificity and generalization in object recognition.Communications biology · 2025Article
- TMBclaw: tumor clone-aware graph learning improves immunotherapy response prediction across heterogeneous cohorts.Briefings in bioinformatics · 2025Article
- Universal scale-free representations in human visual cortex.PLoS computational biology · 2025Article
- Convolutional architectures are cortex-aligned de novo.bioRxiv : the preprint server for biology · 2025Article
- Universal dimensions of visual representation.Science advances · 2025Article
- TopoNets: High performing vision and language models with brain-like topography.... International Conference on Learning Representations · 2025Article
- Poisson Variational Autoencoder.ArXiv · 2024Article
- A large-scale examination of inductive biases shaping high-level visual representation in brains and machines.Nature communications · 2024Article
- A unifying framework for functional organization in early and higher ventral visual cortex.Neuron · 2024Article
- Factorized visual representations in the primate visual system and deep neural networks.eLife · 2024Article
- Disentangled deep generative models reveal coding principles of the human face processing network.PLoS computational biology · 2024Article
- Article
- Many but not all deep neural network audio models capture brain responses and exhibit correspondence between model stages and brain regions.PLoS biology · 2023Article
- Hierarchical VAEs provide a normative account of motion processing in the primate brain.bioRxiv : the preprint server for biology · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Geometric descriptions of deep neural networks (DNNs) have the potential to uncover core representational principles of computational models in neuroscience. Here we examined the geometry of DNN models of visual cortex by quantifying the latent dimensionality of their natural image representations. A popular view holds that optimal DNNs compress their representations onto low-dimensional subspaces to achieve invariance and robustness, which suggests that better models of visual cortex should have lower dimensional geometries. Surprisingly, we found a strong trend in the opposite direction-neural networks with high-dimensional image subspaces tended to have better generalization performance when predicting cortical responses to held-out stimuli in both monkey electrophysiology and human fMRI data. Moreover, we found that high dimensionality was associated with better performance when learning new categories of stimuli, suggesting that higher dimensional representations are better suited to generalize beyond their training domains. These findings suggest a general principle whereby high-dimensional geometry confers computational benefits to DNN models of visual cortex.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.