Towards a Rigorous Science of Interpretable Machine Learning.

Doshi-Velez, F., & Kim, B. (2017). Towards a Rigorous Science of Interpretable Machine Learning. arXiv preprint.

Type

Preprint

Intellectual base

Grey literature

Year

2017

Link

https://arxiv.org/abs/1702.08608

Cited from

futurism_foresight, philosophy

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Causal Layered Analysis (CLA)
  • Doshi-Velez and Kim (2017) make a closely related point about machine-learning interpretability, arguing that explanation must address multiple levels — surface predictions, model mechanics, and the design assumptions framing the problem.

    This sourceDefines ML interpretability and proposes a taxonomy of evaluation, arguing explanation must address multiple levels (surface predictions, model mechanics, and the design assumptions framing the problem).

• Interpretation
  • … shows the structural pattern survives the loss of human convention; what remains is the directed move from medium to meaning under a framework — exactly the activity Doshi-Velez and Kim (2017) frame as the proper object of interpretability research, the explanation of a model's decision in terms a human can audit.

    This sourceFrames ML interpretability as the activity of producing explanations of model decisions in terms a human auditor can evaluate, and proposes a taxonomy of evaluation (application-grounded, human-grounded, functionally-grounded) for that activity.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:b8102f9c5f71 · see in the full table