18087976. AUTOMATED GROUND TRUTH GENERATION USING A NEURO-SYMBOLIC METAMODEL simplified abstract (Cisco Technology, Inc.)
Contents
AUTOMATED GROUND TRUTH GENERATION USING A NEURO-SYMBOLIC METAMODEL
Organization Name
Inventor(s)
Hugo Latapie of Long Beach CA (US)
Ozkan Kilic of Long Beach CA (US)
Adam James Lawrence of Pasadena CA (US)
Ramana Rao V. R. Kompella of Cupertino CA (US)
AUTOMATED GROUND TRUTH GENERATION USING A NEURO-SYMBOLIC METAMODEL - A simplified explanation of the abstract
This abstract first appeared for US patent application 18087976 titled 'AUTOMATED GROUND TRUTH GENERATION USING A NEURO-SYMBOLIC METAMODEL
The abstract describes a device that receives a request for ground truth examples to train a machine learning model, based on context data provided by the requestor. The device uses a metamodel with a semantic reasoner and a sub-symbolic layer to identify and label the ground truth examples, which are then provided to the requestor.
- Simplified Explanation:
- Device receives request for ground truth examples for machine learning model training. - Context data about location provided by requestor. - Metamodel with semantic reasoner and sub-symbolic layer used to identify and label examples. - Ground truth examples provided to requestor.
- Key Features and Innovation:
- Use of metamodel with semantic reasoner and sub-symbolic layer. - Context-based identification of ground truth examples. - Provision of labeled examples for machine learning model training.
- Potential Applications:
- Training machine learning models for location-based analysis. - Improving accuracy of machine learning algorithms with labeled ground truth examples.
- Problems Solved:
- Enhancing the quality of training data for machine learning models. - Streamlining the process of obtaining and labeling ground truth examples.
- Benefits:
- Increased accuracy and efficiency in training machine learning models. - Facilitation of location-specific analysis tasks.
- Commercial Applications:
- Optimizing location-based services and recommendations. - Enhancing geospatial data analysis for various industries.
- Questions about the Technology:
1. How does the device differentiate between different types of ground truth examples? 2. What are the potential limitations of using a metamodel for identifying and labeling examples?
- Frequently Updated Research:
- Stay updated on advancements in machine learning model training techniques. - Explore new developments in semantic reasoning and sub-symbolic layers for data analysis.
Original Abstract Submitted
In one embodiment, a device receives, from a requestor, a request for a set of ground truth examples of a particular type to be used to train a machine learning model. The request includes context data regarding a location to be analyzed by the machine learning model. The device identifies, based on the request, the set of ground truth examples using a metamodel comprising a semantic reasoner and a sub-symbolic layer. The device associates labels with the set of ground truth examples. The device provides, to the requestor, the set of ground truth examples and their labels.
