18013053. Generalized Bags for Learning from Label Proportions simplified abstract (GOOGLE LLC)
Contents
- 1 Generalized Bags for Learning from Label Proportions
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Generalized Bags for Learning from Label Proportions - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
Generalized Bags for Learning from Label Proportions
Organization Name
Inventor(s)
Rishi Saket of Bangalore, Karnataka (IN)
Aravindan Raghuveer of Bangalore, Karnataka (IN)
Balaraman Ravindran of Chennai, Tamil Nadu (IN)
Generalized Bags for Learning from Label Proportions - A simplified explanation of the abstract
This abstract first appeared for US patent application 18013053 titled 'Generalized Bags for Learning from Label Proportions
Simplified Explanation
The present disclosure describes a method involving obtaining a plurality of data bags, each containing instances and associated proportion labels, and generating training bags from these data bags based on weights to predict proportion label errors.
- The method involves obtaining multiple data bags, each with instances and proportion labels.
- Training bags are generated from the data bags using weights.
- The predicted proportion label error at the bag level correlates with the predicted error at the instance level.
Potential Applications
This technology could be applied in various fields such as data analysis, machine learning, and predictive modeling.
Problems Solved
This technology helps in predicting proportion label errors accurately, which can improve the performance of machine learning models.
Benefits
The method can enhance the accuracy of predictions and improve the overall performance of machine learning algorithms.
Potential Commercial Applications
This technology could be utilized in industries such as finance, healthcare, and marketing for predictive analytics and decision-making processes.
Possible Prior Art
One possible prior art could be the use of machine learning algorithms for predictive modeling in various industries.
Unanswered Questions
How does this method compare to existing techniques for predicting label errors in machine learning models?
This article does not provide a direct comparison with existing techniques for predicting label errors in machine learning models.
What are the specific industries or applications where this method could have the most significant impact?
The article does not specify the industries or applications where this method could have the most significant impact.
Original Abstract Submitted
Example aspects of the present disclosure relate to an example method. The example method includes obtaining, by a computing system comprising one or more processors, a plurality of data bags. In the example method, each respective data bag of the plurality of data bags comprises a respective plurality of instances and is respectively associated with one or more proportion labels. The example method also includes generating, by the computing system, a plurality of training bags from the plurality of data bags according to a plurality of weights. In the example method, the training bags are generated such that a bag-level predicted proportion label error by a machine-learned prediction model over the plurality of training bags correlates to an instance-level predicted proportion label error by the machine-learned prediction model.
