# US 2022/0019890 A1 · Method and device for creating a machine learning system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0019890 A1
- Document ID: US20220019890A1
- Status: Published application
- Kind: A1
- Application number: 17/372,142
- Filed: 2021-07-09
- Published: 2022-01-20
- Earliest claimed: 2020-07-15
- Applicants: Robert Bosch GmbH
- Inventors: Benedikt Sebastian Staffler; David Stoeckel
- Web page: https://patentgrep.com/patent/US20220019890A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06F 18/211: Selection of the most significant subset of features
- G06F 18/2163: {Partitioning the feature space}
- G06F 18/29: {Graphical models, e.g. Bayesian networks}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06V 10/764: using classification, e.g. of video objects
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for creating a machine learning system. The method includes: providing a directed graph including an input and an output node, each edge being assigned a probability that characterizes at which probability an edge is drawn. The probabilities are initially set to a value that paths are drawn at the same probability starting from the particular edge up to the output node.

## Claims

### Claim 1

A computer-implemented method for creating a machine learning system, the method comprising the following steps:
providing a directed graph having an input node and an output node that are connected via a plurality of edges and nodes, each edge of the edges being assigned a probability that characterizes at which probability the edge is drawn, the probabilities being initially set to a value that paths are drawn at the same probability starting from the edge up to the output node;
randomly drawing a plurality of paths through the graph and training the machine learning systems corresponding to the paths; and
adjusting parameters of the machine learning system and the probabilities of the edges of the path during training, so that a cost function is optimized; and
drawing a path as a function of the adjusted probabilities and creating the machine learning system corresponding to the drawn path.

### Claim 2 (depends on 1)

The method as recited in claim 1, wherein starting from a selected node, all possible paths to the output node are counted, a value of the probability of each edge of those edges that are connected proceeding from the selected node is initially set to a number of the possible paths running via the edge, divided by a number of the counted possible paths.

### Claim 3 (depends on 1)

The method as recited in claim 1, wherein all possible paths up to the output node are counted for each node of the directed graph, a value of the probability of each edge of the edges is initially set to a number of the possible paths from the output node of the edge divided by a number of the possible paths of an input node of the edge.

### Claim 4 (depends on 1)

The method as recited in claim 1, wherein in the process of drawing the path, the path is iteratively created, the subsequent edge being randomly selected at each node from the possible subsequent edges, which are connected to the node, as a function of its assigned probability.

### Claim 5

A non-transitory machine-readable memory medium on which is stored a computer program for creating a machine learning system, the method comprising the following steps:
providing a directed graph having an input node and an output node that are connected via a plurality of edges and nodes, each edge of the edges being assigned a probability that characterizes at which probability the edge is drawn, the probabilities being initially set to a value that paths are drawn at the same probability starting from the edge up to the output node;
randomly drawing a plurality of paths through the graph and training the machine learning systems corresponding to the paths; and
adjusting parameters of the machine learning system and the probabilities of the edges of the path during training, so that a cost function is optimized; and
drawing a path as a function of the adjusted probabilities and creating the machine learning system corresponding to the drawn path.

### Claim 6

A device configured to create a machine learning system, the device configured to:
provide a directed graph having an input node and an output node that are connected via a plurality of edges and nodes, each edge of the edges being assigned a probability that characterizes at which probability the edge is drawn, the probabilities being initially set to a value that paths are drawn at the same probability starting from the edge up to the output node;
randomly draw a plurality of paths through the graph and training the machine learning systems corresponding to the paths; and
adjust parameters of the machine learning system and the probabilities of the edges of the path during training, so that a cost function is optimized; and
draw a path as a function of the adjusted probabilities and create the machine learning system corresponding to the drawn path.
