| CARVIEW |
Machine Learning in Oracle Database Features
Machine Learning in Oracle Autonomous Database
Machine Learning Notebooks
Increase your productivity, whether you’re a data scientist, data engineer, or developer. Oracle Machine Learning Notebooks supports SQL, PL/SQL, Python, R, Conda, and markdown interpreters, so you can work with your language of choice alongside in-database machine learning and custom third-party packages to develop analytical solutions. Collaborate with your broader data science team, schedule notebooks to run automatically, visualize your data and version, and compare notebooks with this built-in notebook environment.
- Oracle Machine Learning Notebooks main documentation
- Using Oracle Machine Learning Notebooks with Autonomous Database documentation
Machine Learning Services
Reduce time to deploy and manage native in-database models and Open Neural Network Exchange (ONNX) format models in the Oracle Autonomous Database environment. Application developers use models through easy-to-integrate REST endpoints. Monitor your data and in-database models to help ensure ongoing correctness and accuracy. Deploy models quickly and easily from the Oracle Machine Learning AutoML and model UIs, and support key aspects of your MLOps requirements.
- REST API for Oracle Machine Learning Services
- Oracle Machine Learning Services documentation
- Data monitoring documentation
- Machine learning model monitoring documentation
- Work with cognitive text functionality
- Examples in GitHub repository
Machine Learning Monitoring
Gain insights into how your enterprise data evolves over time and take corrective action sooner to avoid data issues that can have a significant negative impact on the enterprise. Data monitoring helps you maintain data integrity for your enterprise applications and dashboards. Quickly and reliably identify data drift and understand individual data columns and their interactions. Model monitoring helps identify when your model metric, such as accuracy or R-squared, significantly changes—or the distribution of predicted values deviates too much from initial values. This may signal the need to rebuild or redesign your model. The no-code data and model monitoring UI provides multiple visualizations and metrics to aid you in assessing quality issues.
- Oracle Machine Learning Monitoring main documentation
- Oracle Machine Learning Data Monitoring documentation
- Oracle Machine Learning Model Monitoring documentation
Machine Learning for SQL
Simplify and accelerate the creation of in-database machine learning models by both data scientists and nonexpert users with SQL and PL/SQL for data preparation and model building, evaluation, and deployment.
Machine Learning AutoML UI
This no-code user interface supports AutoML on Oracle Autonomous Database to improve both data scientist productivity and nonexpert user access to powerful in-database algorithms for classification and regression. Rapidly experiment with data, algorithms, and hyperparameters for faster exploration and discovery. Deploy models immediately through SQL queries or to Oracle Machine Learning Services as REST endpoints for seamless integration with applications and real-time scoring. Generate notebooks for selected models, allowing users to further refine and customize models within Oracle Machine Learning Notebooks.
Machine Learning for R
Accelerate machine learning modeling using Oracle Autonomous Database as a high performance computing platform with an R interface. Use Oracle Machine Learning Notebooks or your favorite R integrated development environment (IDE) to develop scalable machine learning–based solutions in R and create Conda environments with third-party packages. Easily deploy user-defined R functions from SQL and REST APIs with system-provided data parallelism and task parallelism.
Machine Learning for Python
Data scientists and other Python users accelerate machine learning modeling and solution deployment by using Oracle Autonomous Database as a high performance computing platform with a Python interface. Use Oracle Machine Learning Notebooks or your favorite Python IDE to develop scalable machine learning–based solutions in Python. Built-in AutoML recommends relevant in-database algorithms and features and performs automated model tuning and selection.
Data Miner
Data scientists and data analysts can use this drag-and-drop user interface to quickly build analytical workflows within Oracle SQL Developer. Rapid model development and refinement let users discover hidden patterns, relationships, and insights in their data.
Machine Learning in Oracle Database
Machine Learning for SQL
Simplify and accelerate the creation of in-database machine learning models for both data scientists and nonexpert users with SQL and PL/SQL for data preparation and model building, evaluation, and deployment.
Data Miner
Data scientists and data analysts can use this drag-and-drop user interface to quickly build analytical workflows within Oracle SQL Developer. Rapid model development and refinement let users discover hidden patterns, relationships, and insights in their data.
Machine Learning for R
Accelerate machine learning modeling using Oracle Database as a high performance computing platform with an R interface. Easily deploy user-defined R functions from SQL and R APIs with system-provided data parallelism and task parallelism. User-defined R functions can include functionality from the R package ecosystem.
- Install Oracle Machine Learning for R
- Technical brief (PDF)
- Oracle Machine Learning for R documentation
- GitHub repository
Machine Learning for Python
Accelerate machine learning modeling using Oracle Database as a high performance computing platform with a Python interface. Built-in AutoML recommends relevant in-database algorithms and features and performs automated model tuning and selection. Easily deploy user-defined Python functions from SQL and Python APIs with system-provided data parallelism and task parallelism. User-defined Python functions can include functionality from the Python package ecosystem.
AutoML
Machine Learning AutoML UI
This no-code user interface supports AutoML on Oracle Autonomous Database to improve both data scientist productivity and nonexpert user access to powerful in-database algorithms for classification and regression. Rapidly experiment with data, algorithms, and hyperparameters for faster exploration and discovery. Deploy models immediately through SQL queries or to Oracle Machine Learning Services as REST endpoints for seamless integration with applications and real-time scoring. Generate notebooks for selected models, allowing users to further refine and customize models within Oracle Machine Learning Notebooks.
- How AI can take the drudgery out of tuning machine learning models
- Oracle Machine Learning AutoML UI documentation
Machine Learning for Python
Data scientists and other Python users accelerate machine learning modeling and solution deployment by using Oracle Autonomous Database and Oracle Database as a high performance computing platform with a Python interface. Built-in AutoML recommends relevant in-database algorithms and features and performs automated model tuning and selection. Together, these capabilities enhance user productivity, model accuracy, and scalability.
No-code user interfaces
Machine Learning AutoML UI
This no-code user interface supports AutoML on Oracle Autonomous Database to improve both data scientist productivity and nonexpert user access to powerful in-database algorithms for classification and regression. Rapidly experiment with data, algorithms, and hyperparameters for faster exploration and discovery. Deploy models immediately through SQL queries or to Oracle Machine Learning Services as REST endpoints for seamless integration with applications and real-time scoring. Generate notebooks for selected models, allowing users to further refine and customize models within Oracle Machine Learning Notebooks.
- How AI can take the drudgery out of tuning machine learning models
- Oracle Machine Learning AutoML UI documentation
Machine Learning Monitoring
Gain insights into how your enterprise data evolves over time and take corrective action sooner to avoid data issues that can have a significant negative impact on the enterprise. Data monitoring helps you ensure data integrity for your enterprise applications and dashboards. Quickly and reliably identify data drift and understand individual data columns and their interactions. Model monitoring helps identify when your model metric, such as accuracy or R-squared, significantly changes—or the distribution of predicted values deviates too much from initial values. This may signal the need to rebuild or redesign your model. The no-code data and model monitoring UI provides multiple visualizations and metrics to aid users in assessing quality issues.
- Oracle Machine Learning Monitoring main documentation
- Oracle Machine Learning Data Monitoring documentation
- Oracle Machine Learning Model Monitoring documentation
Data Miner
Data scientists and data analysts can use this drag-and-drop user interface to quickly build analytical workflows within Oracle SQL Developer. Rapid model development and refinement let users discover hidden patterns, relationships, and insights in their data.