Pith. sign in

REVIEW 1 cited by

Locally Linear Attributes of ReLU Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2012.01940 v1 pith:7I6UG77N submitted 2020-11-30 cs.LG cs.CV

Ben Sattelberg , Renzo Cavalieri , Michael Kirby , Chris Peterson , Ross Beveridge This is my paper · ORCID
classification cs.LGcs.CV
keywords networkneuralspaceaffinedecompositioninputlinearpolytopes
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

A ReLU neural network determines/is a continuous piecewise linear map from an input space to an output space. The weights in the neural network determine a decomposition of the input space into convex polytopes and on each of these polytopes the network can be described by a single affine mapping. The structure of the decomposition, together with the affine map attached to each polytope, can be analyzed to investigate the behavior of the associated neural network.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Pathwise Explanation of ReLU Neural Networks

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A new explanation method for ReLU neural networks that builds piecewise linear models from selected connected subsets of hidden units, called paths, to produce adjustable and decomposable input attributions.

Pith tools