Explainable AI
Tools and frameworks to understand and interpret your machine learning models.
Understand AI output and build trust
What's new
Design interpretable and inclusive AI
Build interpretable and inclusive AI systems from the ground up with tools designed to help detect and resolve bias, drift, and other gaps in data and models. AI Explanations in AutoML Tables, Vertex AI Predictions, and Notebooks provide data scientists with the insight needed to improve datasets or model architecture and debug model performance. The What-If Tool lets you investigate model behavior at a glance.
Deploy AI with confidence
Grow end-user trust and improve transparency with human-interpretable explanations of machine learning models. When deploying a model on AutoML Tables or Vertex AI, you get a prediction and a score in real time indicating how much a factor affected the final result. While explanations don’t reveal any fundamental relationships in your data sample or population, they do reflect the patterns the model found in the data.
Streamline model governance
Simplify your organization’s ability to manage and improve machine learning models with streamlined performance monitoring and training. Easily monitor the predictions your models make on Vertex AI. The continuous evaluation feature lets you compare model predictions with ground truth labels to gain continual feedback and optimize model performance.
Features
Understand AI output with groundbreaking XAI tools, developed by Google Research and used to power AI at Google.
Feature attributions
A managed service for generating feature attributions. Supported methods include Samples Shapely, Integrated Gradients, and XRAI.
Integrated into Vertex AI services, including AutoML Tables and Vision, Vertex AI Prediction, Notebooks, Model Monitoring, and BigQuery ML.
Example-based Explanations
Build better models with actionable explanations to mitigate data challenges.
A managed Approximate Nearest Neighbor service for returning similar examples to new predictions or instances.
Model analysis
An advanced model analysis toolkit to help you better understand models.
Take action in Vertex AI to inspect models through an interactive dashboard with the integrated What-If Tool.
Alternatively, utilize open source with the What-If Tool or the Learning Interpretability Tool.
Customers
Resources
-
AI explanations for Vertex AI
-
Increasing transparency with Google Cloud AI Explanations
-
BigQuery ML features and capabilities
-
Monitoring feature attributions: How Google saved one of the largest ML services in trouble
-
Explaining machine learning models to business users using BigQueryML and Looker
-
BigQuery Explainable AI now in GA to help you interpret your machine learning models
-
Explaining model predictions on structured data
-
AutoML Tables features and capabilities
-
Explaining model predictions on image data
-
Code samples for Explainable AI
-
AI Explainability whitepaper
-
Putting AI principles into action
Pricing
Explainable AI tools are provided at no extra charge to users of AutoML Tables or Vertex AI. Note that Cloud AI is billed for node-hours usage, and running AI Explanations on model predictions will require compute and storage. Therefore, users of Explainable AI may see their node-hour usage increase.
Start building on Google Cloud with $300 in free credits and 20+ always free products.
Tools and frameworks to deploy interpretable and inclusive machine learning models.