Seldon Data Science and Research. Developers of Alibi Explain https://xitter.cf/t.co/SvvkZ4vbwo and Alibi Detect https://xitter.cf/t.co/3zKwz9sXwQ. Slack: https://xitter.cf/t.co/pZo6GwIt4v
Joined July 2021
- Tweets174
- Following65
- Followers79
- Likes11
Pinned Tweet
There is an increasing awareness among practitioners that data drift poses a challenge to the robust deployment of machine learning models.
But what precisely is meant by “drift” and how can we protect ourselves against it? 👇📽️ 🧵
youtube.com/watch?v=JaPMFf0c…
Check out Alex's (@oblibob) blog post on generative modelling using vector-quantized VAEs! seldon.io/generative-modelin…
Seldon Research retweeted
We have a paper accepted into the R2HCAI workshop titled, Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning. 🙌
Very excited to be a part of the conversation around the advances of responsible AI. 💪
Learn more: r2hcai.github.io/AAAI-23/ind…
#AAAI
We are excited to announce the release of Alibi Detect v0.11.0, featuring widened serialisation support and a new backend that allows drift detection to be rapidly performed on large datasets. seldon.io/alibi-detect-v0-11…
This drastically speeds and scales up the detectors to large dataset sizes, with dataset sizes in the order of 100,000’s easily achievable on a single consumer grade GPU.
ALT Scaling of prediction time with KeOps and PyTorch backends.
For more details, check out our example benchmarking drift detectors with the KeOps backend here: docs.seldon.io/projects/alib…
We are pleased to announce the release of Alibi Explain v0.9.0 with support for calculating global feature importance via Permutation Importance or Partial Dependence Variance. github.com/SeldonIO/alibi
Both of these insights are complementary as PI captures not only main feature effects but also interactions, and we recommend considering both, when possible, for a thorough analysis of model behaviour.
Much more information on Permutation Importance and Partial Dependence Variance, including worked examples, can be found on our documentation pages: docs.seldon.io/projects/alib…
docs.seldon.io/projects/alib…
We are delighted to announce the release of Alibi Explain github.com/SeldonIO/alibi v0.8.0 featuring support for Partial Dependence plots, enabling global explainability of any model.
Our PD implementation in Alibi v0.8.0 has the following advantages over other implementations:
- Applies to any black-box model
- Full support for 1-way, 2-way and higher order PD for numerical and categorical variables
- Flexible plotting functionality for 1-way and 2-way PD
For a more extensive discussion of the method, its usage and examples please visit our documentation page: docs.seldon.io/projects/alib….