18330857. Method and Device for Training a Neural Network simplified abstract (Robert Bosch GmbH)
Method and Device for Training a Neural Network
Organization Name
Inventor(s)
Thomas Branz of Esslingen (DE)
Markus Hanselmann of Stuttgart (DE)
Andreas Genssle of Musberg (DE)
Method and Device for Training a Neural Network - A simplified explanation of the abstract
This abstract first appeared for US patent application 18330857 titled 'Method and Device for Training a Neural Network
Simplified Explanation
The abstract describes a method for training a neural network to analyze sensor signals from a technical system and generate output signals for classification or regression purposes. The method involves receiving a sensor signal, using a first neural network to generate a first output signal based on the sensor signal, using a second neural network with a different architecture to generate a second output signal based on the sensor signal, and training the first neural network by adjusting its parameters based on the second output signal.
- The method involves training a neural network to analyze sensor signals and generate output signals.
- Two neural networks are used, with the second network having a different architecture than the first.
- The first neural network is trained by adjusting its parameters based on the output signal generated by the second neural network.
Potential Applications
- This method can be applied in various technical systems where sensor signals need to be analyzed and classified or regressed.
- It can be used in industries such as manufacturing, healthcare, transportation, and robotics to improve system performance and decision-making.
Problems Solved
- The method addresses the challenge of training a neural network to accurately analyze sensor signals and generate meaningful output signals.
- By using a second neural network with a different architecture, the method allows for improved training of the first neural network, leading to better performance and accuracy.
Benefits
- The method provides a more effective way to train neural networks for analyzing sensor signals.
- By adjusting the parameters of the first neural network based on the output signal of the second neural network, the method improves the accuracy and reliability of the analysis.
- The use of different neural network architectures enhances the training process and allows for better adaptation to different types of sensor signals.
Original Abstract Submitted
A method for training a first neural network is disclosed. The neural network is configured to ascertain, based on sensor signals of a technical system, an output signal characterizing a classification and/or a regression result regarding the sensor signal. The method includes (i) during operation of the technical system, receiving a sensor signal of the technical system, (ii) ascertaining a first output signal by way of the first neural network and based on the sensor signal, (iii) ascertaining a second output signal by way of a second neural network and based on the sensor signal, wherein the second neural network has a different architecture than the first neural network, and (iv) training the first neural network by adjusting parameters of the first neural network, wherein the first neural network is trained as a function of the second output signal.
