# US 2019/0378008 A1 · Encoding and decoding information

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

- Number: US 2019/0378008 A1
- Document ID: US20190378008A1
- Status: Published application
- Kind: A1
- Application number: 16/004,671
- Filed: 2018-06-11
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Inait SA
- Applicants: Inait SA
- Inventors: Henry Markram; Ran Levi; Kathryn Pamela Hess Bellwald; Felix Schuermann
- Web page: https://patentgrep.com/patent/US20190378008A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method that is implemented by one or more data processing devices can include receiving a training set that includes a plurality of representations of topological structures in patterns of activity in a source neural network and training a neural network using the representations either as an input to the neural network or as a target answer vector. The activity is responsive to an input into the source neural network.

## Claims

### Claim 1

A device comprising:
a neural network coupled to input representations of topological structures in patterns of activity arising in a source neural network in response to a plurality of different inputs, wherein the neural network is trained to process the representations and produce a responsive output.

### Claim 2 (depends on 1)

The device of claim 1, wherein the topological structures all encompass two or more nodes in the source neural network and one or more edges between the nodes.

### Claim 3 (depends on 1)

The device of claim 1, further comprising:
an actuator coupled to receive the responsive output from the neural network and act upon a real or virtual environment;
a sensor coupled to measure a characteristic of the environment; and
a teacher module configured to interpret the measurements received from the sensor and provide a reward and/or a regret to the neural network.

### Claim 4 (depends on 1)

The device of claim 1, wherein the topological structures comprise simplices.

### Claim 5 (depends on 1)

The device of claim 1, wherein the topological structures enclose cavities.

### Claim 6 (depends on 1)

The device of claim 1, wherein the representations of topological structures represent topological structures that arise in the source neural network exclusively at times during which the patterns of activity have a complexity that is distinguishable from the complexity of other activity that is responsive to the respective of the inputs.

### Claim 7 (depends on 1)

The device of claim 1, wherein the device further comprises
a second neural network trained to produce, in response to a plurality of different inputs, respective approximations of the representations of topological structures in the patterns of activity arising in the source neural network in response to the different inputs.

### Claim 8 (depends on 7)

The device of claim 7, further comprising:
an actuator coupled to receive the responsive output from the neural network and act upon a real or virtual environment; and
a sensor coupled to measure a characteristic of the environment, wherein the second neural network is trained to produce the respective approximations at least in part in response to the measured characteristic of the environment.

### Claim 9 (depends on 8)

The device of claim 8, further comprising:
a teacher module configured to interpret the measurements received from the sensor and provide a reward and/or a regret to the neural network.

### Claim 10 (depends on 1)

The device of claim 1, wherein the representations of topological structures comprise multi-valued, non-binary digits.

### Claim 11 (depends on 1)

The device of claim 1, wherein the representations of topological structures represents the occurrence of the topological structures without specifying where the patterns of activity arise in the source neural network.

### Claim 12 (depends on 1)

The device of claim 1, wherein the device comprises a smart phone.

### Claim 13 (depends on 1)

The device of claim 1, wherein the source neural network is a recurrent neural network.

### Claim 14

A method performed by one or more data processing devices, the method comprising:
receiving a training set, the training set comprising a plurality of representations of topological structures in patterns of activity in a source neural network, wherein the activity is responsive to an input into the source neural network; and
training a neural network using the representations either as an input to the neural network or as a target answer vector.

### Claim 15 (depends on 14)

The method of claim 14, wherein the topological structures all encompass two or more nodes in the source neural network and one or more edges between the nodes.

### Claim 16 (depends on 14)

The method of claim 14, wherein:
the training set further comprises a plurality of input vectors each corresponding to a respective of the representations; and
training the neural network comprises training the neural network using each of the plurality of representations as a target answer vector.

### Claim 17 (depends on 14)

The method of claim 14, wherein:
training the neural network comprises training the neural network using each of the plurality of representations as an input.

### Claim 18 (depends on 17)

The method of claim 17, wherein:
the training set further comprises a plurality of reward or regret values; and
training the neural network comprises reinforcement learning.

### Claim 19 (depends on 14)

The method of claim 14, wherein the topological structures comprise simplices.

### Claim 20 (depends on 14)

The method of claim 14, wherein the topological structures enclose cavities.

### Claim 21 (depends on 14)

The method of claim 14, wherein the representations of topological structures represent topological structures that arise in the source neural network exclusively at times during which the patterns of activity have a complexity that is distinguishable from the complexity of other activity that is responsive to the respective of the inputs.

### Claim 22 (depends on 14)

The method of claim 14, wherein the representations of topological structures comprise multi-valued, non-binary digits.

### Claim 23 (depends on 14)

The method of claim 14, wherein the representations of topological structures represents the occurrence of the topological structures without specifying where the patterns of activity arise in the source neural network.

### Claim 24 (depends on 14)

The method of claim 14, wherein the source neural network is a recurrent neural network.

### Claim 25 (depends on 24)

The method of claim 24, wherein the input to the neural network is a stream of data.
