17643333. VISUALIZATION AND EDITING OF MACHINE LEARNING MODELS simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
VISUALIZATION AND EDITING OF MACHINE LEARNING MODELS
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
VISUALIZATION AND EDITING OF MACHINE LEARNING MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17643333 titled 'VISUALIZATION AND EDITING OF MACHINE LEARNING MODELS
Simplified Explanation
The patent application describes a method for visually editing machine learning models in a computing environment. Here are the key points:
- The method involves receiving a multidimensional dataset and processing it.
- An interactive representation is created, allowing visualization and exploration of multiple datasets and decision boundaries of machine learning models built on the dataset.
- The behavior of the machine learning models can be edited using logical rules or by moving the decision boundaries.
- The interactive representation enables users to easily modify and fine-tune the machine learning models.
Potential applications of this technology:
- Data analysis and exploration: The interactive representation allows users to visually analyze and explore complex datasets, making it useful in various domains such as finance, healthcare, and marketing.
- Model optimization: By editing the behavior of machine learning models, users can optimize their performance and accuracy, leading to better predictions and decision-making.
- Collaborative machine learning: The visual editing capability enables multiple users to collaborate and collectively improve machine learning models.
Problems solved by this technology:
- Complex model editing: Traditional methods for editing machine learning models can be complex and require extensive coding. This technology simplifies the editing process by providing a visual interface.
- Lack of transparency: Machine learning models can be difficult to interpret and understand. The interactive representation allows users to visualize and comprehend the decision boundaries and behavior of the models.
Benefits of this technology:
- User-friendly interface: The visual editing capability makes it easier for users to interact with and modify machine learning models, even without extensive programming knowledge.
- Improved model performance: By fine-tuning the behavior of machine learning models, users can enhance their performance and accuracy.
- Enhanced collaboration: The interactive representation facilitates collaboration among users, enabling them to collectively improve machine learning models.
Original Abstract Submitted
Embodiments are provided for enabling visual editing of machine learning models in a computing environment by a processor. A multidimensional dataset may be received. The multidimensional dataset may be processed. Visualization and exploration of an interactive representation of a plurality of datasets and decision boundaries of one or more machine learning models built upon multidimensional dataset are provided. Behavior of the one or more machine learning models may be edited via the interactive representation using one or more logical rules or moving the decision boundaries of one or more machine learning models.