Machine Learning Model Training with Feature Importance Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning model training methods prioritize accuracy over other important features such as comprehensibility and personalization, which may not be suitable for all applications, and lack a systematic approach to emphasize specific features while maintaining model accuracy.
Innovation Solution
A method and system that identifies and emphasizes specific features like comprehensibility and personalization in machine learning models by using hierarchical clustering to select and weight training data, ensuring the model's accuracy remains above a threshold through iterative permutations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If training data is selected to maximize accuracy, then model accuracy is improved, but other important features like comprehensibility and personalization are compromised
Solution Approach 1:
The patent changes the parameter of training data selection by introducing feature importance weights that can be adjusted. Instead of uniformly weighting all training data, the system assigns different weights based on the importance of features (accuracy, comprehensibility, personalization), allowing the training process to optimize for a customized mix of these parameters rather than just accuracy
Solution Approach 2:
The system dynamically adjusts the training process by allowing flexible selection and weighting of training data based on desired feature priorities. The training methodology adapts its behavior based on which features are most important for a given application, enabling the model to prioritize different characteristics as needed
2Measurement precision
If conventional training methods are used to maximize accuracy, then model accuracy is improved, but the ability to emphasize specific features is lost
Solution Approach 1:
The patent introduces adjustable parameter(s) - specifically feature importance weights - that control the emphasis placed on different features during training. These parameters can be modified to highlight specific features without requiring complex changes to the overall training architecture or methodology
Solution Approach 2:
The training data is segmented and differentiated by feature importance. The system identifies and separates training examples based on which features they contain, then applies different weighting or selection criteria to different segments of the data, allowing fine-grained control over which features are emphasized
Data Source
AI summary
A method, computer program, and computer system are provided for training a machine learning model. A feature associated with training data derived from a dataset is identified. A machine learning model is generated based on the training data. At least a portion of the training data associated with maximizing an importance value associated with the identified feature is selected. The importance value corresponds to a need associated with the machine learning model. One or more weight values is assigned to the selected portion of the training data. The machine learning model is updated based on the assigned weight values.