REVIEW 1 cited by
On neural network kernels and the storage capacity problem
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In this short note, we reify the connection between work on the storage capacity problem in wide two-layer treelike neural networks and the rapidly-growing body of literature on kernel limits of wide neural networks. Concretely, we observe that the "effective order parameter" studied in the statistical mechanics literature is exactly equivalent to the infinite-width Neural Network Gaussian Process Kernel. This correspondence connects the expressivity and trainability of wide two-layer neural networks.
Forward citations
Cited by 1 Pith paper
-
Summary statistics of learning link changing neural representations to behavior
A small set of population-level summary statistics can, in several solvable model classes, predict learning performance, and the authors argue these same statistics should guide analysis of neural recordings of learning.
Discussion (0). Continue with ORCID to comment.