Model calculating unit and control unit for selectively calculating an RBF model, a gaussian process model and an MLP model

A control unit, comprising:

• a microprocessor;
• and
• one or multiple model calculating units for selectively calculating an RBF model or a neural layer of a multilayer perceptron model, each of the model calculating units including a hardwired processor core configured completely in hardware to calculate a definitely specified computing algorithm in coupled functional blocks, the processor core being configured to calculate an output variable for an RBF model as a function of:
• (i) one or multiple input variables of an input variable vector, (ii) supporting points, (iii) length scales, and (iv) parameters specified for each of the supporting points, the processor core furthermore being configured to calculate an output variable for each neuron of a neural layer of a multilayer perceptron model having a number of neurons as a function of:
• (i) the one or the multiple input variables of the input variable vector, (ii) a weighting matrix having weighting factors, and (iii) an offset value specified for each of the neurons;
• wherein each of the one or more model calculating units is hardwired, is formed completely in hardware, and is not capable of executing software code;
• wherein each processor core is configured to perform, based on a selection variable, a selection between (i) the calculation of the output variable for the RBF model, and (ii) the calculation of each output variable for each neuron of the neural layer of the multilayer perceptron model;
• wherein the control unit is configured to receive detected sensor signals from a sensor system in an internal combustion engine as the input variable vector, and to control the internal combustion engine as a function of the calculated output variable.