Machine Learning Model Segmentation for Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Machine learning technologies face challenges in being optimized for specific use cases, leading to suboptimal accuracy due to pre-configured solutions not being tailored to particular applications, where experts in machine learning may lack domain knowledge and domain experts may not understand machine learning algorithms, resulting in impracticality in configuring or managing models.
Innovation Solution
The development of customizable machine learning solutions that allow users to define filters for training data sets, train multiple model segments, and specify hyperparameters for improved accuracy, enabling the selection of appropriate model segments and hyperparameter values based on user input and requests, thereby enhancing the precision of machine learning results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If pre-configured machine learning scenarios are provided for particular solutions, then ease of operation is improved, but manufacturing precision deteriorates
Solution Approach 1:
The patent divides a single machine learning model into multiple model segments, each trained on filtered subsets of the training data set. Filters are applied to create different segments based on specific criteria, allowing each segment to specialize in particular aspects of the data. This segmentation enables both ease of operation through automated filtering and improved accuracy by having specialized segments for different data characteristics.
Solution Approach 2:
Different model segments are trained with different filter configurations to achieve local optimization. Each segment has specialized knowledge for specific data patterns or domains, allowing the system to select the most appropriate segment for each query. This local quality approach ensures high accuracy for specific use cases while maintaining overall system versatility.
2Manufacturing precision
If multiple model segments are trained with different filters, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The system automatically manages the complexity of multiple model segments through self-service mechanisms. When a query is received, the system automatically selects the appropriate model segment based on the query characteristics and filter criteria, without requiring manual intervention. This automation handles the complexity internally while presenting a simple interface to users, resolving the contradiction between multiple segments and manageable complexity.
3Manufacturing precision
If hyperparameter values are customized for specific scenarios, then manufacturing precision is improved, but ease of operation deteriorates
Solution Approach 1:
Hyperparameter values and filter configurations are predetermined and pre-configured for different model segments during the training phase. This preliminary action allows the system to have optimized parameters ready for specific scenarios without requiring users to manually tune hyperparameters at query time. The complexity of hyperparameter optimization is performed in advance, maintaining both accuracy and ease of operation during deployment.
Data Source
AI summary
Techniques and solutions are described for facilitating the use of machine learning techniques. In some cases, filters can be defined for multiple segments of a training data set. Model segments corresponding to respective segments can be trained using an appropriate subset of the training data set. When a request for a machine learning result is made, filter criteria for the request can be determined and an appropriate model segment can be selected and used for processing the request. One or more hyperparameter values can be defined for a machine learning scenario. When a machine learning scenario is selected for execution, the one or more hyperparameter values for the machine learning scenario can be used to configure a machine learning algorithm used by the machine learning scenario.