Exercising artificial intelligence by refining model output
A technology of artificial intelligence and models, applied in computing models, database models, transmission systems, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0017] At least some embodiments described herein relate to improved training of artificial intelligence. Raw output data is obtained by applying an input dataset to an artificial intelligence (AI) model. Such raw output data is sometimes difficult to interpret. For example, an AI model tailored for video recognition might recognize a list of objects, relationships, confidence levels, etc. over time. Certain information (eg, the presence of a pen) may not have any association at all. In fact, raw output may contain large amounts of irrelevant or not-so-relevant data. The principles defined in this paper provide a systematic approach to refine the output for various AI models.
[0018] Artificial intelligence (AI) model ensemble representation structures are used for the purpose of refining the AI model output and thus are more useful. For, and perhaps for, each AI model in a large number of AI models, the representation structure represents a refinement of the output dat...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


