Method and device for ascertaining a gradient of a data-based function model

Patent metadata

Field	Value
Publication number	US-10402509-B2
Application number	US-201414558544-A
Country	US
Kind code	B2
Filing date	Dec 2, 2014
Priority date	Dec 3, 2013
Publication date	Sep 3, 2019
Grant date	Sep 3, 2019

Abstract

In a method for calculating a gradient of a data-based function model, having one or multiple accumulated data-based partial function models, e.g., Gaussian process models, a model calculation unit is provided, which is designed to calculate function values of the data-based function model having an exponential function, summation functions, and multiplication functions in two loop operations in a hardware-based way, the model calculation unit being used to calculate the gradient of the data-based function model for a desired value of a predefined input variable.

First claim

What is claimed is:

1. A method for calculating an inverse data-based function model of a data-based function model having at least one accumulated data-based partial function model, comprising:
calculating, in only hardware using a first hardware core of a multi-core model calculation unit, a function value of the data-based function model having an exponential function, at least one summation function, and at least one multiplication function in two loop operations in a hardware-based way; and
calculating, in only hardware using a second hardware core of the multi-core model calculation unit, a gradient of the data-based function model for a desired value of a predefined input variable;
wherein the calculating, using the first hardware core of the multi-core model calculation unit, the function value of the data-based function model, and the calculating, using the second hardware core of the multi-core model calculation unit, the gradient of the data-based function model, are carried out in parallel;
calculating the inverse data-based function model depending on both the function value of the data-based function model and the gradient of the data-based function model;
wherein the inverse data-based function model calculates, for a given output value of the data-based function model, an input value of the data-based function model.

2. The method as recited in claim 1 , wherein:
each of the data-based partial function models of the data-based function model is defined by supporting point data, hyperparameters, and a parameter vector having a number of elements which corresponds to the number of the supporting point data points of the relevant data-based partial function model; and
the data-based function model is modified to calculate the gradient of the data-based function model by applying a weighting vector, which is dependent on supporting point data points, to the parameter vector.

3. The method as recited in claim 2 , wherein the gradient of the data-based function model is calculated by the model calculation unit as a function value of the modified data-based function model for the desired value of the predefined input variable, and an offset value is added.

4. The method as recited in claim 3 , wherein the supporting point data points are scaled and the sum of the function value of the modified data-based function model and the offset value are multiplied by a factor which is based on the standard deviation of the supporting point data with regard to the output data, to obtain the gradient of the data-based function model.

5. The method as recited in claim 3 , wherein a weighting vector, which is dependent on supporting point data points, is applied repeatedly to the parameter vector during a calculation of the modified data-based function model.

6. The method as recited in claim 1 , wherein:
each of the data-based partial function models of the data-based function model is defined by supporting point data, hyperparameters, and a parameter vector, the parameter vector containing a number of elements which corresponds to the number of the supporting point data points; and
the data-based function model is modified to calculate the gradient of the data-based function model with respect to a predefined input variable by calculating the function value of the data-based function model in the model calculation unit for a desired value of the predefined input variable, multiplying the result by the desired value of the predefined input variable, and subsequently carrying out a renewed calculation of the data-based function model using a changed parameter vector in the model calculation unit.

7. The method as recited in claim 1 , wherein the calculation of the function value of the data-based function model, and the calculation of the gradient of the data-based function model, are implemented in only hardware in permanently wired fashion.

8. A control module for calculating an inverse data-based function model of a data-based function model having at least one accumulated data-based partial function model, comprising:
a main computing unit; and
a multi-core model calculation unit having a first hardware core configured to calculate in only hardware function values of the data-based function model having an exponential function, summation functions, and multiplication functions in two loop operations, and a second hardware core configured to calculate in only hardware a gradient of the data-based function model for a desired value of a predefined input variable;
wherein the first hardware core of the multi-core model calculation unit carries out the calculating of the function value of the data-based function model in parallel with the second hardware core of the multi-core model calculation unit calculating the gradient of the data-based function model;
wherein the control module is configured to calculate the inverse data-based function model depending on both the function value of the data-based function model and the gradient of the data-based function model;
wherein the inverse data-based function model calculates, for a given output value of the data-based function model, an input value of the data-based function model.

9. The control module of claim 8 , wherein:
each of the data-based partial function models of the data-based function model is defined by supporting point data, hyperparameters, and a parameter vector having a number of elements which corresponds to the number of the supporting point data points of the relevant data-based partial function model; and
the data-based function model is modified to calculate the gradient of the data-based function model by applying a weighting vector, which is dependent on supporting point data points, to the parameter vector.

10. The control module of claim 9 , wherein the gradient of the data-based function model is calculated by the model calculation unit as a function value of the modified data-based function model for the desired value of the predefined input variable, and an offset value is added.

11. The control module of claim 10 , wherein a weighting vector, which is dependent on supporting point data points, is applied repeatedly to the parameter vector during a calculation of the modified data-based function model.

12. The control module as recited in claim 8 , wherein the calculation of the function value of the data-based function model, and the calculation of the gradient of the data-based function model, are implemented in only hardware in permanently wired fashion.

13. A non-transitory, computer-readable data storage medium storing a computer program having program codes which, when executed on a computer, perform a method for calculating an inverse data-based function model of a data-based function model having at least one accumulated data-based partial function model, the method comprising:
calculating, in only hardware using a first hardware core of a multi-core model calculation unit, a function value of the data-based function model having an exponential function, at least one summation function, and at least one multiplication function in two loop operations in a hardware-based way;
calculating, in only hardware using a second hardware core of the multi-core model calculation unit, a gradient of the data-based function model for a desired value of a predefined input variable;
wherein the calculating, using the first hardware core of the multi-core model calculation unit, the function value of the data-based function model, and the calculating, using the second hardware core of the multi-core model calculation unit, the gradient of the data-based function model, are carried out

Assignees

• Bosch Gmbh Robert

Inventors

• Hanselmann Michael
• Koehler Jan Mathias
• Markert Heiner

Classifications

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• F02D41/28 Primary

  Interface circuits · CPC title

• G06F17/17

  Function evaluation by approximation methods, e.g. inter- or extrapolation, smoothing, least mean square method ({G06F17/18 takes precedence } ; interpolation for numerical control G05B19/18) · CPC title

• F02D41/2438

  Active learning methods · CPC title

• F02D2041/1433

  using a model or simulation of the system · CPC title