Bring Your Own Model to Your Database for AI and ML [LRN3616].pdf

1、Bring Your Own Model to Your Database for AI and ML LRN3616Mark HornickAbi Giles-HaighMarcos ArancibiaSeptember 11,2024Oracle CloudWorld Copyright 2024,Oracle and/or its affiliates1The following is intended to outline our general product direction.It is intended for information purposes only,and may

2、 not be incorporated into any contract.It is not a commitment to deliver any material,code,or functionality,and should not be relied upon in making purchasing decisions.The development,release,timing,and pricing of any features or functionality described for Oracles products may change and remains a

3、t the sole discretion of Oracle Corporation.The materials in this presentation pertain to Oracle Health,Oracle,Oracle Cerner,and Cerner Enviza which are all wholly owned subsidiaries of Oracle Corporation.Nothing in this presentation should be taken as indicating that any decisions regarding the int

4、egration of any EMEA Cerner and/or Enviza entities have been made where an integration has not already occurred.Oracle CloudWorld Copyright 2024,Oracle and/or its affiliates2Safe harbor statementMark HornickSenior Director,Product ManagementMachine Learning and AIAbi Giles-HaighCoachNewcastle United

5、 WomensMarcos ArancibiaSenior Principal Product ManagerAutonomous DatabaseOracle CloudWorld Copyright 2024,Oracle and/or its affiliates3SpeakersMultiple sources of modelsOracle CloudWorld Copyright 2024,Oracle and/or its affiliates4Machine learning models capture patterns in data and make prediction

6、s using a variety of algorithmsNative OML in-database modelsML models produced using Native Python and R packagesTransformers/embedding modelsONNX-format modelsWhat is ONNX?Oracle CloudWorld Copyright 2024,Oracle and/or its affiliates5Open Neural Network Exchange(ONNX)ONNX is an open format built to