# US 2021/0064995 A1 · Method, device and computer program for creating a pulsed neural network

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

- Number: US 2021/0064995 A1
- Document ID: US20210064995A1
- Status: Published application
- Kind: A1
- Application number: 16/937,353
- Filed: 2020-07-23
- Published: 2021-03-04
- Earliest claimed: 2019-08-28
- Assignees: Robert Bosch GmbH
- Applicants: Robert Bosch GmbH
- Inventors: Thomas Pfeil; Alexander Kugele
- Web page: https://patentgrep.com/patent/US20210064995A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/09: Supervised learning
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method for creating a pulsed neural network (Spiking Neural Network). The method begins with an assignment of a predefinable control pattern (rollout pattern) to a deep neural network. This is followed by a training of the deep neural network using the control pattern. This is followed by a conversion of the deep neural network into the pulsed neural network, the connections of the pulsed neural network being assigned a delay, in each case as a function of the control pattern. A computer program, a device for carrying out the method, and to a machine-readable memory element are also described.

## Claims

### Claim 1

A method for creating a pulsed neural network (Spiking Neural Network) by converting a deep neural network into a pulsed neural network, comprising the following steps:
assigning a predefinable control pattern to the deep neural network, the control pattern characterizing a sequence of calculations, according to which layers or neurons of the deep neural network ascertain their intermediate variables, and the control pattern characterizing which of the layers or of the neurons of the deep neural network ascertain their intermediate variable independently of the sequence;
training the deep neural network using the control pattern; and
converting the deep neural network into the pulsed neural network, delays assigned to connections of the pulse neural network and/or to neurons of the pulsed neural network being selected as a function of the control pattern.

### Claim 2 (depends on 1)

The method as recited in claim 1, wherein the deep neural network includes at least one bridging connection, wherein during conversion of the deep neural network into the pulsed neural network, the assigned delay of the bridging connection of the pulsed neural network is selected by the bridging connection as a function of the control pattern and/or as a function of a number of layers of the deep neural network bridged by the bridging connection.

### Claim 3 (depends on 1)

The method as recited in claim 1, wherein during the training, parameters and/or intermediate variables of the deep neural network are quantized.

### Claim 4 (depends on 1)

The method as recited in claim 1, wherein the control pattern corresponds to a streaming control pattern.

### Claim 5 (depends on 1)

The method as recited in claim 1, wherein a spatial signal dropout is used during the training.

### Claim 6 (depends on 1)

The method as recited in claim 1, wherein training input variables of the deep neural network are each arranged multiple times in succession to form a sequence of identical input variables or the training input variables are sequences of temporally successive input variables, and wherein the deep neural network is trained based on the sequences.

### Claim 7 (depends on 1)

The method as recited in claim 1, wherein after the conversion, the pulsed neural network is operated as a function of the delays, and during the operation of the pulsed neural network, weights of the connections of the pulsed neural network are scaled within time steps, during which an input variable is present at the input of the pulsed neural network.

### Claim 8 (depends on 7)

The method as recited in claim 7, wherein during the operation of the pulsed neural network, input variables of the pulsed neural network are sequences or time series of event-based recordings of an event-based camera.

### Claim 9

A non-transitory machine-readable memory element on which is stored a computer program for creating a pulsed neural network (Spiking Neural Network) by converting a deep neural network into a pulsed neural network, the computer program, when executed by a computer, causing the computer to perform the following steps:
assigning a predefinable control pattern to the deep neural network, the control pattern characterizing a sequence of calculations, according to which layers or neurons of the deep neural network ascertain their intermediate variables, and the control pattern characterizing which of the layers or of the neurons of the deep neural network ascertain their intermediate variable independently of the sequence;
training the deep neural network using the control pattern; and
converting the deep neural network into the pulsed neural network, delays assigned to connections of the pulse neural network and/or to neurons of the pulsed neural network being selected as a function of the control pattern.

### Claim 10

A device configured to create a pulsed neural network (Spiking Neural Network) by converting a deep neural network into a pulsed neural network, the device configured to:
assign a predefinable control pattern to the deep neural network, the control pattern characterizing a sequence of calculations, according to which layers or neurons of the deep neural network ascertain their intermediate variables, and the control pattern characterizing which of the layers or of the neurons of the deep neural network ascertain their intermediate variable independently of the sequence;
train the deep neural network using the control pattern; and
convert the deep neural network into the pulsed neural network, delays assigned to connections of the pulse neural network and/or to neurons of the pulsed neural network being selected as a function of the control pattern.

### Claim 11

A non-transitory computer readable medium on which is stored a pulsed neural network, the pulsed neural network being formed by performing, by a computer, the following steps:
assigning a predefinable control pattern to a deep neural network, the control pattern characterizing a sequence of calculations, according to which layers or neurons of the deep neural network ascertain their intermediate variables, and the control pattern characterizing which of the layers or of the neurons of the deep neural network ascertain their intermediate variable independently of the sequence;
training the deep neural network using the control pattern; and
converting the deep neural network into the pulsed neural network, delays assigned to connections of the pulse neural network and/or to neurons of the pulsed neural network being selected as a function of the control pattern.
