Method for training an artificial neural network, artificial neural network, use of an artificial neural network, and corresponding computer program, machine-readable memory medium, and corresponding apparatus

A non-transitory machine-readable memory medium on which is stored a computer program, which when executed controls a method for training an artificial neural network, for controlling a technical system, by way of training data sets, the method comprising:

• adapting a parameter of the artificial neural network depending on a loss function, the loss function including a first term that represents an estimate of a lower bound of distances between classifications of the training data sets by the artificial neural network and expected classifications of the training data sets, wherein the loss function includes a second term that is configured in such a way that differences in aleatoric uncertainty in the training data sets over different samples of the artificial neural network are regulated.

An artificial neural network for controlling a technical system, the artificial neural network being trained using training data sets, including adaptation of a parameter of the artificial neural network depending on a loss function, the loss function including a first term that represents an estimate of a lower bound of distances between classifications of the training data sets by the artificial neural network and expected classifications of the training data sets, wherein the loss function includes a second term that is configured in such a way that differences in aleatoric uncertainty in the training data sets over different samples of the artificial neural network are regulated.

A method, comprising:

• providing an artificial neural network for controlling a technical system, the artificial neural network being trained using training data sets, including adaption of a parameter of the artificial neural network depending on a loss function, the loss function including a first term that represents an estimate of a lower bound of distances between classifications of the training data sets by the artificial neural network and expected classifications of the training data sets, wherein the loss function includes a second term that is configured in such a way that differences in aleatoric uncertainty in the training data sets over different samples of the artificial neural network are regulated;
• and
• controlling the technical system using the trained artificial neural network, the technical system including a robot, or a vehicle, or a tool, or a machine.

A non-transitory machine-readable memory medium on which is stored a computer program, the computer program, when executed by a computer, causing the computer to perform the following steps:

• providing an artificial neural network for controlling a technical system, the artificial neural network being trained using training data sets, including adaption of a parameter of the artificial neural network depending on a loss function, the loss function including a first term that represents an estimate of a lower bound of distances between classifications of the training data sets by the artificial neural network and expected classifications of the training data sets, wherein the loss function includes a second term that is configured in such a way that differences in aleatoric uncertainty in the training data sets over different samples of the artificial neural network are regulated;
• and
• controlling the technical system using the trained artificial neural network, the technical system including a robot, or a vehicle, or a tool, or a machine.

An apparatus for controlling a technical system, the apparatus comprising:

• an artificial neural network for controlling a technical system, the artificial neural network being trained using training data sets, including adaptation of a parameter of the artificial neural network depending on a loss function, the loss function including a first term that represents an estimate of a lower bound of distances between classifications of the training data sets by the artificial neural network and expected classifications of the training data sets, wherein the loss function includes a second term that is configured in such a way that differences in aleatoric uncertainty in the training data sets over different samples of the artificial neural network are regulated.