ML Control System Hyperparameter Search Against Overfitting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Machine learning systems, such as neural networks, often memorize training data rather than generalizing it, which is problematic for safety-critical applications like automated driving, as they may not perform well with new data points.

Innovation Solution

The method automatically determines architectural and optimization parameters through a parameter search, preventing the system from memorizing training data and enhancing its generalization capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If machine learning systems are trained with traditional methods using fixed hyperparameters, then training can be completed efficiently, but the system memorizes training data and fails to generalize to new data points

Engineering Contradiction:
Improvegeneralization capabilityVSAvoidparameter search complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically determining its own hyperparameters through the parameter search. The control system autonomously identifies optimal values for learning rate, batch size, and other hyperparameters without requiring manual intervention or external expertise, enabling the system to improve its own generalization capability while maintaining operational simplicity for users

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The invention applies parameter changes by systematically varying hyperparameters (learning rate, batch size, number of epochs) during the training process. The control system explores different parameter combinations to identify optimal settings that prevent overfitting and enhance generalization, transforming fixed-parameter training into adaptive parameter optimization

Inventive Principle:
Principle #35Parameter changes

2Reliability

If hyperparameters are chosen based on empirical knowledge or validation dataset performance, then training efficiency is maintained, but the system may still memorize training data due to insufficient parameter optimization

Engineering Contradiction:
Improvegeneralization performanceVSAvoidparameter search time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by conducting a comprehensive parameter search before final model deployment. The control system pre-identifies optimal hyperparameter combinations through systematic exploration, ensuring that the model is properly configured for generalization before being deployed to production environments, thereby preventing time loss during later validation phases

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The invention implements feedback mechanisms where the control system continuously monitors training performance metrics and uses this information to adjust hyperparameter selection. The system learns from validation performance and iteratively refines parameter choices, creating a closed-loop optimization process that balances exploration time with generalization improvement

Inventive Principle:
Principle #23Feedback

3Adaptability or versatility

If the number of parameters in the neural network is much larger than the number of data points, then the model capacity increases, but the risk of memorizing training data increases significantly

Engineering Contradiction:
Improvemodel capacityVSAvoidoverfitting risk
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system applies parameter changes by dynamically adjusting both architectural parameters (network depth, width, filter sizes) and optimization parameters (learning rate schedules, regularization strengths) during training. This allows the model to adapt its capacity to match the complexity of the underlying data patterns rather than blindly increasing parameters, thereby maintaining high adaptability while controlling overfitting risk through data-driven parameter selection

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3853778B1Method and device for operating a control system
Publication Date: 2024.10.09 ROBERT BOSCH GMBH
  • EP3853778B1 patent drawingFigure 1
  • EP3853778B1 patent drawingFigure 2
  • EP3853778B1 patent drawingFigure 3

AI summary

The invention relates to a method for parameterizing a machine learning system (60), in particular a neural network, which is configured to determine an associated class (y) of a plurality of classes from input data (x), wherein the machine learning system (60) is trained once with correctly labeled training data, and once with not correctly labeled training data. Hyperparameters (θH) of the machine learning system (60) are selected in such a way that the respective trained machine learning system (60) can reproduce actual classifications (y T ) of the correctly labeled training data better than actual classifications of the not correctly labeled training data (y T ).