Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) · HackerPapers discussions

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) — mentioned by genmon

Wed, 08 Mar 2023 19:58:29 GMT

Now that's an interesting regression! I don't remember seeing it there before. (The worst I've noticed before has been Lawrence of Arabia under History of the Ancient World. Very much 20th century really.) Several other classifications are arguable -- which I think shows one of the limitations of this technique: it's not possible to iterate + improve. So instead I've been wondering about using the embeddings of each episode synopsis, and comparing to the embeddings of Dewey subdivisions. I should be able to tune the results better that way. There's also a technique from Google called CAVs…

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

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) — HN submission

Tue, 05 Feb 2019 15:04:37 GMT

Interpretability Beyond Feature Attribution

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) — mentioned by ssivark

Mon, 28 Jan 2019 05:34:46 GMT

I found it easier to understand the idea by skimming the introduction in the paper [1]: > TCAV uses directional derivatives to quantify the model prediction’s sensitivity to an underlying high-level concept [...] For instance, given an ML image model recognizing zebras, and a new, user-defined set of examples defining ‘striped’, TCAV can quantify the influence of striped concept to the ‘zebra’ prediction as a single number. In addition, we conduct statistical tests where CAVs are randomly re-learned and rejected unless they show a significant and stable correlation with a model output class…

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

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) — mentioned by irhshafkat

Wed, 23 Jan 2019 19:57:20 GMT

Thanks, glad to hear you enjoyed the article! I'm currently working on applications in road safety, and have also recently taken up an interest in learning about interpretability and fairness in machine learning models (for instance, I really loved this paper: https://arxiv.org/abs/1711.11279 and am working on making an easily accessible implementation of it). Another thing that caught my attention is how deep learning is being used to build new developer tools, such as models that read code and automatically generate comments. There's just so much ground to cover, simply because deep…

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

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) — HN submission

Wed, 11 Apr 2018 22:19:02 GMT

Google Brain: Concept Activation Vectors

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.