explainX explainable AI framework now supports H2O.ai models and provides explanations on multiple levels
Modular explainability structure for flexible and customizable model insights on a local level.
Learn how explainable AI is positioned to accelerate the adoption of AI in healthcare.
Feature engineering, model interpretability and model behavior stress-test are crucial for the success of your machine learning models before production.
In this deep dive, we will explain a CatBoost Classifier model by using explainX. You can simply follow the code and explain your model behaviour as well.
Introducing updates in the explainX open-source explainable AI library: Cohort Analysis, Evaluate Model Performance & Improved Visualizations
Convincing business stakeholders to trust our models is challenging. ExplainX makes it easier for data scientists to go from raw data to insights.
Use explainX Prototypical Analysis: An Examples Based Reasoning for Effective Decision Making
The need for transparent, responsible & ethical AI is urgent. Learn what role governments play in accelerating explainable Ai.
Navigating explainability techniques can be quite perplexing. Read this guide to start with explainable AI.
This talk was given at the Federated & Distributed Machine Learning Conference 2020.
Facing challenges around AI fairness, ethics and governance.
As artificial intelligence (AI) systems gain industry-wide adoption and the government calls for regulations, the need to explain and build trust in automated decisions by these AI systems is more crucial than ever.