Pith. sign in

REVIEW 3 cited by

Learning how to explain neural networks: PatternNet and PatternAttribution

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 1705.05598 v2 pith:YHSKJKIS submitted 2017-05-16 stat.ML cs.LG

Pieter-Jan Kindermans , Kristof T. Schütt , Maximilian Alber , Klaus-Robert Müller , Dumitru Erhan , Been Kim , Sven Dähne This is my paper · ORCID
classification stat.MLcs.LG
keywords linearnetworksmodelsneuralexplanationdeepmethodspatternattribution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linear models are simple neural networks. We argue that explanation methods for neural nets should work reliably in the limit of simplicity, the linear models. Based on our analysis of linear models we propose a generalization that yields two explanation techniques (PatternNet and PatternAttribution) that are theoretically sound for linear models and produce improved explanations for deep networks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. In Defense of Information Leakage in Concept-based Models

    cs.LG 2026-06 conditional novelty 7.0 of 10

    Concept-based models can use controlled 'benign' information leakage to remain accurate and intervenable under real-world concept incompleteness by reframing their training objective.

  2. TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    TEVI applies sparse autoencoders and caption-conditioned masking to edit image embeddings, yielding better retrieval on MS COCO, Flickr, IIW, DOCCI, and RoCOCO benchmarks with larger gains on richer captions.

  3. Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks

    cs.CV 2025-09 conditional novelty 6.0 of 10

    An unsupervised method, EDDP, jointly learns encoding-decoding direction pairs for concepts in CNN latent spaces, recovering interpretable and influential concepts without labels, validated on synthetic and real data.

Pith tools