Pith. sign in

REVIEW 2 cited by

From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks

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

arxiv 2310.11884 v2 pith:2JGDGNJU submitted 2023-10-18 cs.AI cs.CLcs.CVcs.LGcs.NE

classification cs.AIcs.CLcs.CVcs.LGcs.NE
keywords conceptsneurallearningreasoningsystemnetworksexplainingknowledge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate those concepts with a reasoning system for inference or use a reasoning system to act upon them to improve or enhance the learning system. On the other hand, knowledge can not only be extracted from neural networks but concept knowledge can also be inserted into neural network architectures. Since integrating learning and reasoning is at the core of neuro-symbolic AI, the insights gained from this survey can serve as an important step towards realizing neuro-symbolic AI based on explainable concepts.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. On the Performance of Concept Probing: The Influence of the Data (Extended Version)

    cs.AI 2025-07 conditional novelty 7.0 of 10

    A systematic empirical study shows concept probes need surprisingly little data for task-relevant concepts, tolerate data reuse and moderate label noise, and benefit slightly from larger probed models.

  2. Survival Concept-Based Learning Models

    cs.LG 2025-02 conditional novelty 6.0 of 10

    SurvCBM and SurvRCM combine concept bottleneck learning with Cox and Beran survival models, and SurvCBM achieves the best C-index and concept F1 on synthetic MNIST and CIFAR experiments.

Pith tools