Model Learning System Exclusion Determination Unit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated re-learning of machine learning models in smart city environments often fails to improve accuracy, leading to unnecessary resource wastage when the model's accuracy does not increase or decreases.
Innovation Solution
A model learning system that includes a server with a data acquisition unit, a training data set creation unit, and an exclusion determination unit, which evaluates the model's accuracy and temporarily excludes it from re-learning if it does not improve, preventing wasteful re-processing and requesting external expertise for improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the learning model is automatically re-learned to improve accuracy, then the model accuracy may improve, but when accuracy does not improve or decreases, arithmetic resources are wasted
Solution Approach 1:
The system implements a feedback mechanism where the model accuracy is evaluated after each re-learning cycle. The exclusion determination unit compares the post-learning accuracy with the pre-learning accuracy and provides feedback to the learning control unit. When accuracy does not improve or deteriorates, the model is excluded from further automatic re-learning, preventing wasteful consumption of arithmetic resources while maintaining the ability to re-learn when beneficial.
2Productivity
If automatic re-learning is repeated without evaluation, then the learning process continues, but unnecessary re-learning wastes limited arithmetic resources
Solution Approach 1:
The system performs a preliminary evaluation of model accuracy before initiating the re-learning process. The exclusion determination unit assesses whether the model should be included in automatic re-learning based on pre-learning accuracy metrics. This preliminary action filters out models that would not benefit from re-learning, ensuring that arithmetic resources are allocated only to models with potential for improvement.
3Loss of energy
If the learning model is excluded from re-learning when accuracy does not improve, then arithmetic resources are conserved, but the model cannot be re-optimized
Solution Approach 1:
The system dynamically adjusts the re-learning status of models based on real-time accuracy evaluation. The exclusion determination unit continuously monitors model accuracy and can include or exclude models from automatic re-learning based on their performance. This dynamic approach allows the system to allocate arithmetic resources flexibly, enabling re-optimization when conditions are favorable while conserving resources when re-learning would be futile.
Data Source
AI summary
A model learning system includes a device in which a learning model is used, a data acquisition device that acquires data used for creating a training data set for the learning model, and a model learning device that automatically learns the learning model using the training data set for the learning model created using the data. The model learning device is configured to, when a model accuracy after automatically learning the learning model decreases or does not increase compared to before learning, exclude the learning model from a target to be automatically learned.