JDATA_BLOG Telegram 338
💥 Список библиотек для XAI

Хочу зафиналить год useful постом, который лежит у меня дольше, чем ..... ладно, просто долго!

💫Основные библиотеки для моделей ML (и DL)

LIME https://github.com/marcotcr/lime
— ELI5 https://eli5.readthedocs.io/en/latest/
— SHAP https://github.com/slundberg/shap
— DICE ML https://interpret.ml/DiCE/dice_ml.html#
— Pdpbox https://pdpbox.readthedocs.io/en/latest/

☄️Для моделей Deep Learning и LLM

* Captum (pytorch) https://github.com/pytorch/captum
* Anchors https://github.com/marcotcr/anchor
* DALEX https://github.com/ModelOriented/DALEX
* AIX360 https://github.com/IBM/AIX360
* ALIBI https://github.com/SeldonIO/alibi
* Quantus https://github.com/understandable-machine-intelligence-lab/Quantus
* OmniXAI https://github.com/salesforce/OmniXAI
* pytorch_explain https://github.com/pietrobarbiero/pytorch_explain
* DeepExplain https://github.com/marcoancona/DeepExplain
* Grad-CAM https://github.com/ramprs/grad-cam
* Integrated Gradients https://github.com/ankurtaly/Integrated-Gradients
* DeepLIFT https://github.com/kundajelab/deeplift
* interpret-text https://github.com/interpretml/interpret-text?ysclid=ldebiwr4jr824513795
* ExBERT https://github.com/bhoov/exbert
* ExplainaBoard (NLP) https://github.com/neulab/ExplainaBoard
* CARLA https://github.com/carla-recourse/CARLA

Никому не верьте, и всегда сомневайтесь в моделях!
5🔥3



tgoop.com/jdata_blog/338
Create:
Last Update:

💥 Список библиотек для XAI

Хочу зафиналить год useful постом, который лежит у меня дольше, чем ..... ладно, просто долго!

💫Основные библиотеки для моделей ML (и DL)

LIME https://github.com/marcotcr/lime
— ELI5 https://eli5.readthedocs.io/en/latest/
— SHAP https://github.com/slundberg/shap
— DICE ML https://interpret.ml/DiCE/dice_ml.html#
— Pdpbox https://pdpbox.readthedocs.io/en/latest/

☄️Для моделей Deep Learning и LLM

* Captum (pytorch) https://github.com/pytorch/captum
* Anchors https://github.com/marcotcr/anchor
* DALEX https://github.com/ModelOriented/DALEX
* AIX360 https://github.com/IBM/AIX360
* ALIBI https://github.com/SeldonIO/alibi
* Quantus https://github.com/understandable-machine-intelligence-lab/Quantus
* OmniXAI https://github.com/salesforce/OmniXAI
* pytorch_explain https://github.com/pietrobarbiero/pytorch_explain
* DeepExplain https://github.com/marcoancona/DeepExplain
* Grad-CAM https://github.com/ramprs/grad-cam
* Integrated Gradients https://github.com/ankurtaly/Integrated-Gradients
* DeepLIFT https://github.com/kundajelab/deeplift
* interpret-text https://github.com/interpretml/interpret-text?ysclid=ldebiwr4jr824513795
* ExBERT https://github.com/bhoov/exbert
* ExplainaBoard (NLP) https://github.com/neulab/ExplainaBoard
* CARLA https://github.com/carla-recourse/CARLA

Никому не верьте, и всегда сомневайтесь в моделях!

BY Data Blog




Share with your friend now:
tgoop.com/jdata_blog/338

View MORE
Open in Telegram


Telegram News

Date: |

Choose quality over quantity. Remember that one high-quality post is better than five short publications of questionable value. Clear Select: Settings – Manage Channel – Administrators – Add administrator. From your list of subscribers, select the correct user. A new window will appear on the screen. Check the rights you’re willing to give to your administrator. Telegram channels enable users to broadcast messages to multiple users simultaneously. Like on social media, users need to subscribe to your channel to get access to your content published by one or more administrators. To upload a logo, click the Menu icon and select “Manage Channel.” In a new window, hit the Camera icon.
from us


Telegram Data Blog
FROM American