Abstract: In a method for reducing and/or correcting deviations from a target gradient of a magnetic field gradient created by an MR system input data is provided for a trained function trained by a machine-learning algorithm, wherein the input data comprises information about the target gradient of the MR system. The trained function further creates output data with the aid of the input data. The deviations from the target gradient of the magnetic field gradient created by the MR system are reduced and/or corrected with the aid of the output data created.

Abstract: A deviation from a target gradient of a magnetic field gradient created by an MR system is reduced or corrected. The MR system includes an amplifier, which amplifies an amplifier input signal and outputs an amplifier output signal, and a gradient coil, which creates the magnetic field gradient with the aid of the amplifier output signal. Input data is provided for a trained function trained by a machine-learning algorithm. The input data includes information about the target gradient of the MR system. Output data is created by the trained function with the aid of the input data. A gradient characterization function of the gradient coil is determined. The deviation from the target gradient of the magnetic field gradient created by the MR system is reduced and/or corrected. A deviation caused by the amplifier is reduced and/or corrected with the aid of the output data created, and a deviation caused by the gradient coil is reduced and/or corrected with the aid of the gradient characterization function.

Abstract: In a method for reducing and/or correcting deviations from a target gradient of a magnetic field gradient created by an MR system input data is provided for a trained function trained by a machine-learning algorithm, wherein the input data comprises information about the target gradient of the MR system. The trained function further creates output data with the aid of the input data. The deviations from the target gradient of the magnetic field gradient created by the MR system are reduced and/or corrected with the aid of the output data created.

Abstract: A deviation from a target gradient of a magnetic field gradient created by an MR system is reduced or corrected. The MR system includes an amplifier, which amplifies an amplifier input signal and outputs an amplifier output signal, and a gradient coil, which creates the magnetic field gradient with the aid of the amplifier output signal. Input data is provided for a trained function trained by a machine-learning algorithm. The input data includes information about the target gradient of the MR system. Output data is created by the trained function with the aid of the input data. A gradient characterization function of the gradient coil is determined. The deviation from the target gradient of the magnetic field gradient created by the MR system is reduced and/or corrected. A deviation caused by the amplifier is reduced and/or corrected with the aid of the output data created, and a deviation caused by the gradient coil is reduced and/or corrected with the aid of the gradient characterization function.