Shapley Values Explained | Interpretability for AI models, even LLMs!

Ever wondered how to interpret your machine learning models? 🤔 We explain a powerful interpretability technique for machine learning models: Shapley Values. They can be used to explain any model. 💻 We show a simple example code of how they work, and then 📖 explain the theory behind them.

Thanks to our Patrons who support us in Tier 2, 3, 4: 🙏
Dres. Trost GbR, Siltax, Vignesh Valliappan, Michael, Sunny Dhiana, Andy Ma

Outline:
00:00 Interpretability in AI
01:02 AssemblyAI (Sponsor)
02:23 Simple example
03:51 Code example: SHAP
05:17 Shapley Values explained
07:59 Shortcomings of Shapley Values

▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀
🔥 Optionally, pay us a coffee to help with our Coffee Bean production! ☕
Join this channel to get access to perks:
▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀

🔗 Links:

#AICoffeeBreak #MsCoffeeBean #MachineLearning #AI #research​

Video editing: Nils Trost

[AICoffeeBreak]

Maybe I should have mentioned this in the video: A huge problem in AI interpretability is faithfulness vs. plausibility. Users like *plausible* explanations which look right to them ("aha, this makes sense!"). But sometimes they see things that are counterintuitive or attributions that make no sense to them. Then, even if the explanations are *faithful* to the model's workings, they will seem alien, weird, and users will dislike such a model, or blame it into the interpretability method.

Why is feature attribution seldomly used in production? Because they can help users game the system. 😅 If you know your credit score is low because you have two cars, you will sell that extra car and increase your score.

[DerPylz]

It's always great to see "old" ideas getting used for solving new problems . I had heard about shapley values and was hoping you'd make a video explainer about it Thanks!

[MyrLin]

Very nice training vid. gj. useful info. good examples and references.

[SUD]

Excellent! Always providing the goods.

[vietvu]

The explaination was farrrr better than anything I expected :D very well done

[juanmanuelcirotorres]

A serie about interpretability would be awesome

[manolisnikolakakis]

Thanks for another great explanation! Good luck with your thesis :)

[md.enamulhoq]

best of luck with your Thesis. Stay sound. Love You

[AGI-Bingo]

This is really cool, I can imagine in the future we'll have really good interpretability tools, for example marking a piece of text from the llm output and it will highlight the tokens from the context that influenced it the most ❤

[dianai]

Interpretability was the rabbit hole that got me into deep leaning, would love to see more content on this topic (and if you need ideas on things to explore, lmk) ♥ (also, SHAP was one of the earliest interpretability techniques I came cross after meeting the researcher working on it at the University of Washington at a poster session--so great to see how far this work has come since then!)

[Nif]

This is really interesting and your explanation was excellent, but... did that coffee bean really just wink at me?

[Ben_D.]

Came for the AI commentary. Stayed for the god level lipstick.

[abhishekshakya]

Thanks for referencing the mathematical equations from research papers. It really validates the authenticity of your work. I felt the video was rushed a bit. I was probably expecting a longer video with more examples.
But I understand you might have time crunch with your thesis. Good luck ✌

[harumambaru]

are those acoustic boards for walls? RLHF pretty easy to get all the words as another eastern european english speaker

[sifonios]

Hm. I would have liked to watch this but the background music is far too loud and very distracting. ... Ah it does stop after a while. Yes it is very interesting and useful for me :)

[gordonfreeman]

Not gonna lie, I think that this is basically useless on autoregressive models.