17524374. DYNAMICALLY ENHANCING SUPERVISED LEARNING simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

DYNAMICALLY ENHANCING SUPERVISED LEARNING

Organization Name

International Business Machines Corporation

Inventor(s)

Mukundan Sundararajan of Bangalore (IN)

Siddharth K. Saraya of Raniganj (IN)

DYNAMICALLY ENHANCING SUPERVISED LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17524374 titled 'DYNAMICALLY ENHANCING SUPERVISED LEARNING

Simplified Explanation

The present invention is about a method to improve supervised learning by modifying factors based on user input.

  • Users can select an object that is displayed incorrectly and provide a reason for the error.
  • The user input is analyzed to identify the factor causing the incorrect outcome.
  • The factor is dynamically adjusted to generate a decision path that leads to a correct outcome.
  • The modified decision is then sent to the model or application owner for validation and further training of the machine learning model.

Potential Applications

This technology has potential applications in various fields, including:

  • Machine learning and artificial intelligence systems.
  • Image recognition and computer vision.
  • Natural language processing and text analysis.
  • Fraud detection and anomaly detection.
  • Recommendation systems and personalized content delivery.

Problems Solved

The technology addresses the following problems:

  • Incorrect outcomes in supervised learning models.
  • Difficulty in identifying the specific factors causing incorrect results.
  • Lack of a dynamic approach to modify factors and improve decision paths.
  • Limited ability to incorporate user feedback and refine machine learning models.

Benefits

The technology offers several benefits:

  • Enhanced accuracy and reliability of supervised learning models.
  • Improved user experience by addressing incorrect outcomes.
  • Dynamic modification of factors to optimize decision paths.
  • Incorporation of user feedback for continuous model refinement.


Original Abstract Submitted

Embodiments of the present invention provide an approach for dynamically enhancing supervised learning using factor modification based on parsing user input. A user selects an object being displayed incorrectly and provides input as to the reason. The user input is parsed to derive a factor that is contributing to the false outcome. The factor is dynamically altered resulting in a decision path that produces a positive outcome. The change is sent to a model or application owner for final validation and refined training of the machine learning model.