The Mythos of Model Interpretability · HackerPapers discussions

The Mythos of Model Interpretability — mentioned by owenshen24

Mon, 04 May 2020 05:11:49 GMT

Zachary Lipton has a really good taxonomy of the different things people refer to when they talk about interpretability and explainability here: https://arxiv.org/pdf/1606.03490.pdf

Paper and discussion history. A mention is not an endorsement.

The Mythos of Model Interpretability — mentioned by mlthoughts2018

Mon, 20 Jan 2020 14:24:01 GMT

I work professionally in machine learning for over ten years now and I deeply dispute what you say, and many other practitioners do as well. > “not particularly clear how the features actually interact to reach the prediction.“ This is quite true of many models, such as linear regression in the wild. You may also have a clear but wrong picture of how features interact, eg looking at coefficients of interaction terms in a misspecified linear model. See for example, “The Mythos of Model Interpretability” - https://arxiv.org/abs/1606.03490 Without a coherent definition of what “not black box” or…

Paper and discussion history. A mention is not an endorsement.

The Mythos of Model Interpretability — mentioned by 1_over_n

Sat, 04 Jan 2020 23:48:37 GMT

This is a great point. There is a general lack of understanding about what it means for models to be interpretable & explainable. These words get thrown around often by people who don't understand the definition, and also the trade off with accuracy. Some papers i found interesting on the subject: https://arxiv.org/abs/1606.03490 https://arxiv.org/abs/1707.03886 https://arxiv.org/abs/1806.07552 https://arxiv.org/abs/1702.08608 (i found this was a good sumary of the issues)

Paper and discussion history. A mention is not an endorsement.

The Mythos of Model Interpretability — mentioned by mlthoughts2018

Sat, 04 Jan 2020 23:29:29 GMT

“Explainability” is a subjective idea that allows people to act as gatekeepers about the use of a model through arbitrary politics. “The Mythos of Model Interpretability” is good reading on this. https://arxiv.org/pdf/1606.03490.pdf

Paper and discussion history. A mention is not an endorsement.

The Mythos of Model Interpretability — mentioned by DanWaterworth

Thu, 19 Jul 2018 07:43:12 GMT

You may prefer this link: https://arxiv.org/abs/1606.03490

Paper and discussion history. A mention is not an endorsement.

The Mythos of Model Interpretability — mentioned by ylem

Wed, 08 Feb 2017 18:58:26 GMT

The following article has an interesting treatment of interpretability: https://arxiv.org/pdf/1606.03490.pdf

Paper and discussion history. A mention is not an endorsement.

The Mythos of Model Interpretability — HN submission

Tue, 19 Jul 2016 09:09:53 GMT

The Mythos of Model Interpretability

56 points; 20 discussion replies on HN. Paper and source history. A submission is not an endorsement.