Machine Learning Model Ensemble via Data Aggregation Circuit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating and maintaining robust machine learning models is challenging due to the need for large high-quality data sets and variability in training data, leading to inconsistent model performance across different algorithms and environments.
Innovation Solution
Combining machine learning models through a data-aggregation circuit and computer server to create a new data set from output data processed by multiple circuits, which is then used to train and update machine learning operations, enhancing model robustness and stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple machine learning models are trained with different training data sets, then model robustness is improved, but device complexity and training resource requirements increase
Solution Approach 1:
The system segments the machine learning training process by dividing it into multiple independent model training operations, where each model is trained on a different training data set. This segmentation allows for parallel processing and independent optimization of each model while maintaining overall system robustness.
Solution Approach 2:
The system merges multiple machine learning models into a unified ensemble structure that combines their predictions. By merging the outputs of individual models trained on different data sets, the system achieves improved robustness and reliability while managing complexity through structured integration.
2Reliability
If multiple machine learning models are trained with different training data sets, then model robustness is improved, but training time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and preparing multiple training data sets in advance, organizing them into structured formats before model training begins. This preliminary preparation reduces the overall training time by eliminating redundant data processing steps during the actual model training phase.
Solution Approach 2:
The system maintains continuity of useful action by implementing overlapping training phases where models can be trained in parallel on different data sets, and by implementing incremental update mechanisms that allow continuous learning without complete retraining, thereby reducing total training time.
3Manufacturing precision
If a large data set is used for training, then model quality is improved, but data processing time and storage requirements increase
Solution Approach 1:
The system segments the large training data set into multiple smaller, specialized data sets that can be processed independently for training different models. This segmentation maintains model quality by ensuring each model receives relevant, high-quality training data while reducing the computational burden of processing the entire large data set for each model.
Data Source
AI summary
A combination of machine learning models is provided, according to certain aspects, by a data-aggregation circuit, and a computer server. The data-aggregation circuit is used to assimilate respective sets of output data from at least one of a plurality of circuits to create a new data set, the respective sets of output data being related in that each set of output data is in response to a common data set processed by the machine learning circuitry in the at least one of the plurality of circuits. The computer server uses the new data set to train machine learning operations in at least one of the plurality of circuits.