Dynamic Feature Selection for ML Classification Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional machine learning models face inefficiencies and inaccuracies due to analyzing excessive feature data, leading to false negatives and false positives in object identification, causing a drain on computational resources.
Innovation Solution
A framework is introduced to identify and focus on the most important features relevant to specific runtime environments, customizing the training and deployment of classifiers to enhance accuracy and efficiency by prioritizing vital information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional machine learning models analyze all available feature data, then comprehensive object classification is achieved, but false negatives and false positives increase and computational resources are drained
Solution Approach 1:
The patent extracts and removes irrelevant features from the input data before classification. The system identifies and eliminates features that do not contribute to the specific classification task, reducing the feature set to only those that are relevant for the given runtime environment and classifying object, thereby improving both accuracy and efficiency
Solution Approach 2:
The patent applies different feature selection strategies to different classification contexts. Instead of using a uniform feature set for all classifications, the system dynamically selects features based on the specific runtime environment and target class, making the feature set locally optimized for each classification task
2Adaptability or versatility
If machine learning models are trained with all features, then complete pattern recognition is achieved, but model complexity and training time increase
Solution Approach 1:
The patent performs feature selection and relevance assessment before the actual classification training. By pre-identifying and selecting only the relevant features for each classification task, the system reduces the dimensionality of the training data, which simplifies the model structure and reduces training time while maintaining pattern recognition capability
Solution Approach 2:
The patent segments the feature set into relevant and irrelevant portions based on the specific classification task. This segmentation allows the model to focus only on the necessary features for each classification problem, reducing overall model complexity while preserving the ability to recognize relevant patterns
Data Source
AI summary
Disclosed are systems and methods for improving interactions with and between computers in content providing, streaming and/or hosting systems supported by or configured with devices, servers and/or platforms. The disclosed systems and methods provide a novel machine learning framework that trains classifiers to identify specific features of input data. When implementing these trained classifiers in specific runtime environments, the important features of those specific environments can be identified and leveraged for directing the classifier to the vital information that is relevant to the environment. A customized classifier is thereby dynamically created and deployed which improves how data can be classified, thereby reducing false negatives and positives, and increasing confidence and reliance on how such classifiers can be implemented.