Multisensor Encoding With Adversarial Redundancy Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for machine learning with IoT devices face challenges in efficiently reducing data dimensions and eliminating redundancy in sensor data from multiple instruments, leading to decreased communication efficiency due to redundant information.
Innovation Solution
A machine learning device that includes an acquisition unit, encoding units, an estimation unit, and adversarial estimation units, trained through machine learning to encode and eliminate redundant information by optimizing encoding models and adversarial estimation models to match and mismatch estimated values with correct answers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If sensor data from multiple measuring devices is independently processed through separate neural networks, then each device can perform local processing, but redundant information is generated in the low-dimensional observation data
Solution Approach 1:
The patent merges the independently processed low-dimensional observation data from multiple measuring devices into a unified representation space. By combining the outputs of separate neural networks and applying adversarial training to eliminate redundancy, the system achieves both local processing capability and information efficiency, resolving the contradiction between ease of operation and information loss.
2Loss of energy
If the number of nodes in intermediate layers is reduced to decrease data transmission volume, then communication efficiency improves, but information capacity may be compromised
Solution Approach 1:
The patent applies parameter changes through adversarial training to optimize the encoding models. By adjusting the parameters of the neural networks during training, the system achieves compact low-dimensional representations that minimize communication data volume while preserving essential information capacity, thus resolving the contradiction between energy loss and information loss.
3Productivity
If adversarial training is applied to eliminate redundancy between encoding models, then communication efficiency improves, but training complexity increases
Solution Approach 1:
The patent implements feedback mechanisms through adversarial training where encoding models are trained to generate representations that are difficult for other models to reconstruct. This feedback loop continuously refines the models to eliminate redundancy, achieving improved communication efficiency while managing training complexity through systematic optimization.
Data Source
AI summary
A machine learning device that trains a first encoding model for encoding first sensor data into first code, a second encoding model for encoding second sensor data into second code, and an estimation model for making estimation using the first code and the second code such that an estimation result from the estimation model conforms to correct answer data, trains a first adversarial estimation model that outputs an estimated value of the second code in response to the input of the first code such that the estimated value of the second code estimated by the first adversarial estimation model conforms to the second code outputted from the second encoding model, and trains the first encoding model such that the estimated value of the second code estimated by the first adversarial estimation model does not conform to the second code outputted from the second encoding model.