Discover and read the best of Twitter Threads about #XAI

Most recents (6)

One of the biggest criticisms of the field of post hoc #XAI is that each method "does its own thing", it is unclear how these methods relate to each other & which methods are effective under what conditions. Our #NeurIPS2022 paper provides (some) answers to these questions. [1/N]
In our #NeurIPS2022 paper, we unify eight different state-of-the-art local post hoc explanation methods, and show that they are all performing local linear approximations of the underlying models, albeit with different loss functions and notions of local neighborhoods. [2/N]
By doing so, we are able to explain the similarities & differences between these methods. These methods are similar in the sense that they all perform local linear approximations of models, but they differ considerably in "how" they perform these approximations [3/N]
Read 13 tweets
There seems to be an almost willful confusion about the need and role for explainability of #AI systems on #AI twitter.

Contrary to the often polarizing positions, it is neither the case that we always need explanations nor is it the case that we never need explanations. 🧵1/
We look for explanations of high level decisions of (what for us are) explicit knowledge tasks; and where contestability and collaboration are important.

We rarely look for explanations of tacit knowledge/low level control decisions. 2/
I don't need explanation on why you see a dog in a picture; why you put your left foot 3 mm ahead of your left, or why facebook recommends me yet another page.

I do want one if am denied a loan, or I need a better model of you so I can coordinate with you. 3/
Read 14 tweets
New article on #websites #classification discussing possible #taxonomy that can be used (IAB, Google, Facebook, etc.) as well as #machinelearning models:
explainableaixai.github.io/websitesclassi…

list of useful resources: linktr.ee/airesearcher
a new telegram channel where will post about #explainableai (#XAI for short):
t.me/s/explainablea…
there are now many useful libraries available for doing #explainability of #AI models: SHAP, LIME, partial dependence plots PDP. And also the "classical" feature importance.
Our german blog on topic of website #categorizations: kategorisierungen.substack.com
Read 6 tweets
Interested in interpretable and explainable machine learning? Check out our new blog post with opinions on the field and 70 summaries of recent papers, by @__Owen___ and me!

Link: alignmentforum.org/posts/GEPX7jgL…
Topics include Theory, Evaluation, Feature Importance, Interpreting Representations, Generating Counterfactuals, Finding Influential Data, Natural Language Explanations, Adversarial/Robust Explanations, Unit Testing, Explaining RL Agents, and others (note: not a formal taxonomy)
We're excited to highlight the wide array of research in interpretability/transparency/explainability. We hope this work can help others identify common threads across research areas and get up to speed on the latest work in different subareas.
Read 4 tweets
Really existed about our #UAI2020 paper with @IAugenstein & @vageeshsaxena.

TX-Ray: interprets and quantifies adaptation/transfer during self-supervised pretraining and supervised fine-tuning -- i.e. explores transfer even without probing tasks. #ML #XAI
arxiv.org/abs/1912.00982 Image
TX-Ray adapts the activation maximization idea of "visualizing a neuron's preferred inputs" to discrete inputs - NLP. With a neuron as an 'input preference distribution' we can measure neuron input-preference adaptation or transfer. This works for self- & supervised models alike. Image
We analyzed how neuron preferences are build and adapted during: (a) pretraining, (b) 'zero-shot' application to a new domain, and (c) by supervised fine-tuning.

(a) Confirms that: pretraining learns POS first, as @nsaphra showed, and that preferences converge like perplexity. Image
Read 6 tweets
Je reprends mon thread sur #AInight19 pour la conférence sur l'explicabilité de l'IA, notamment avec David Sadek de @thalesgroup
Inutile de dire que c'est un sujet hyper à la mode.
Petite référence au papier de @Quantmetry
Read 26 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!