# US 2021/0275083 A1 · Systems and methods for training a neurome that emulates the brain of a user

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

- Number: US 2021/0275083 A1
- Document ID: US20210275083A1
- Status: Published application
- Kind: A1
- Application number: 17/188,298
- Filed: 2021-03-01
- Published: 2021-09-09
- Earliest claimed: 2020-03-04
- Assignees: Hi LLC
- Applicants: Hi LLC
- Inventors: Bryan Johnson; Ethan Pratt; Jamu Alford; Husam Katnani; Julian Kates-Harbeck; Ryan Field; Gabriel Lemer; Antonio H. Lara
- Web page: https://patentgrep.com/patent/US20210275083A1

## CPC

- A61B 5/7267: {involving training the classification device}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- G06F 3/015: {Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection}
- G06N 3/004: Artificial life, i.e. computing arrangements simulating life
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/02: Neural networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety}
- G06F 2218/00: Aspects of pattern recognition specially adapted for signal processing
- G06Q 30/0242: Determining effectiveness of advertisements
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A system for training a neurome that emulates a brain of a user comprises a non-invasive brain interface assembly configured for detecting neural activity of the user in response to analog instances of a plurality of stimuli peripherally input into the brain of the user from at least one source of content, memory configured for storing a neurome configured for outputting a plurality of determined brain states of an avatar in response to inputs of the digital instances of the plurality of stimuli, and a neurome training processor configured for determining a plurality of brain states of the user based on the detected neural activity of the user, and modifying the neurome based on the plurality of determined brain states of the user and the plurality of determined brain states of the avatar.

## Claims

### Claim 1

A system for training a neurome that emulates a brain of a user, comprising:
a non-invasive brain interface assembly configured for detecting neural activity of the user in response to analog instances of a plurality of stimuli peripherally input into the brain of the user from at least one source of content;
memory configured for storing a neurome, wherein the neurome is configured for outputting a plurality of determined brain states of an avatar in response to inputs of the digital instances of the plurality of stimuli, wherein the neurome comprises:
a feature extraction component configured for extracting single-dimensional vectors of content features from the digital instances of the plurality of stimuli characterizing the at least one source of content; and
a brain state regression model having a first input and a second input, wherein the neurome training processor is configured for modifying the neurome by inputting the single-dimensional vectors of content features into the first input of the brain state regression model, and single-dimensional vectors of brain state features characterizing the determined brain states of the user into the second input of the brain state regression model, such that the brain state regression model outputs single-dimensional vectors of brain state features of the avatar that substantially match the single-dimensional vectors of brain state features of the user; and
a neurome training processor configured for determining a plurality of brain states of the user based on the detected neural activity of the user, and modifying the neurome based on the plurality of determined brain states of the user and the plurality of determined brain states of the avatar.

### Claim 2 (depends on 1)

The system of claim 1, further comprising one or more peripheral sensors configured for detecting peripheral physiological activity of the user in response to the analog instances of the plurality of stimuli peripherally input into the brain of the user from the at least one source of content, and the neurome training processor is configured for modifying the neurome further based on the detected peripheral physiological activity.

### Claim 3 (depends on 1)

The system of claim 1, wherein the neurome training processor is further configured for acquiring a personal profile of the user, and for modifying the neurome further based on the acquired personal profile.

### Claim 4 (depends on 3)

The system of claim 3, wherein the personal profile comprises one or more of an internet browsing history of the user, a reading history of the user, and autobiographical information of the user.

### Claim 5 (depends on 1)

The system of claim 1, wherein at least some of the plurality of different brain states of the user are different from each other, and at least some of the plurality of determined brain states of the avatar are different from each other.

### Claim 6 (depends on 1)

The system of claim 1, wherein the plurality of determined brain states of the user comprises a plurality of physiological brain states of the user, and the plurality of brain state of the avatar comprises a plurality of physiological brain states of the avatar.

### Claim 7 (depends on 6)

The system of claim 6,
wherein the detected neural activity of the user comprises multi-dimensional time series of neural data;
wherein the brain state training processor is configured for extracting brain state features from the time series of neural data characterizing the plurality of determined brain states of the user, and modifying the neurome based on the plurality of determined brain states of the avatar and the extracted brain state features characterizing the plurality of determined brain states of the user.

### Claim 8 (depends on 7)

The system of claim 7, wherein the neurome training processor comprises a deep convolutional neural network configured for outputting the sets of the extracted brain state features respectively characterizing the plurality of determined brain states of the user in response to an input of the multi-dimensional time series of neural data.

### Claim 9 (depends on 6)

The system of claim 6, wherein neurome training processor is configured for acquiring a plurality of mental brain states of the user in response to the analog instances of the plurality of stimuli peripherally input into the brain of the user from the at least one source of content, and modifying the neurome based on the plurality of determined mental brain states of the user.

### Claim 10 (depends on 9)

The system of claim 9, wherein the neurome training processor is configured for correlating the plurality of acquired mental brain states of the user respectively to the plurality of determined physiological brain states of the user, and modifying the neurome based on the plurality of acquired mental brain states by storing the correlated plurality of acquired mental brain states of the user respectively and plurality of determined physiological brain states of the user in the neurome.

### Claim 11 (depends on 10)

The system of claim 10, further comprising a user interface configured for receiving conscious input from the user indicating the plurality of mental brain states of the user in response to the plurality of analog stimulus instances, wherein the neurome training processor is configured for acquiring the plurality of mental brain states of the user from the user interface.

### Claim 12 (depends on 1)

The system of claim 1, wherein the plurality of determined brain states of the user comprises a plurality of mental brain states of the user, and the plurality of brain states of the avatar comprises a plurality of mental brain states of the avatar.

### Claim 13 (depends on 12)

The system of claim 12, wherein the neurome training processor is configured for determining a plurality of physiological brain states of the user based on the detected neural activity of the user, and determining the plurality of mental states of the user based on the plurality of determined physiological brain states of the user.

### Claim 14 (depends on 1)

The system of claim 1, wherein the neurome is configured for extracting content features from the digital instances of the plurality of stimuli characterizing the at least one source of content, and determining the plurality of determined brain states of the avatar based on the extracted content features.

### Claim 15 (depends on 1)

The system of claim 1, wherein the neurome training processor is configured for modifying the neurome, such that the plurality of determined brain states of the avatar substantially matches the plurality of determined brain states of the user.

### Claim 16 (depends on 15)

The system of claim 15, wherein the neurome training processor comprises:
a comparator configured for comparing the plurality of determined brain states of the avatar and the plurality of determined brain states of the user and respectively generating a plurality of error signals; and
a controller configured for modifying the neurome in a manner that is predicted to minimize the plurality of error signals.

### Claim 17

(canceled)

### Claim 18 (depends on 1)

The system of claim 1, wherein the brain state regression model comprises a deep neural network.

### Claim 19 (depends on 1)

The system of claim 1, further comprising a stimulus conditioning pre-processor configured for generating the digital instances of the plurality of stimuli.

### Claim 20 (depends on 19)

The system of claim 19, wherein the at least one source of content is at least one real-world source of content, and the stimulus conditioning pre-processor is configured for acquiring the analog instances of the plurality of stimuli from the at least one real-world source of content, and generating the digital instances of the plurality of stimuli based on the acquired analog instances of the plurality of stimuli.

### Claim 21 (depends on 20)

The system of claim 20, wherein the stimulus conditioning pre-processor is configured for generating the digital instances of the plurality of stimuli by digitizing the acquired analog instances of the plurality of stimuli.

### Claim 22 (depends on 20)

The system of claim 20, wherein the stimulus conditioning pre-processor is configured for identifying the acquired analog instances of the plurality of stimuli, acquiring at least one virtual source of content, and generating the digital instances of the plurality of stimuli from the acquired at least one virtual source of content that characterizes the acquired analog instances of the plurality of stimuli.

### Claim 23 (depends on 20)

The system of claim 20, wherein the stimulus conditioning pre-processor is configured for acquiring at least one virtual source of content, generating the digital instances of the plurality of stimuli from the acquired at least one virtual source of content, and generating the analog instances of the plurality of stimuli from the generated digital instances of the plurality of stimuli.

### Claim 24 (depends on 23)

The system of claim 23, wherein the neurome training processor is configured for instructing the stimulus conditioning pre-processor to select or modify the at least one virtual source of content based on the plurality of determined brain states of the user.

### Claim 25 (depends on 24)

The system of claim 24, wherein the stimulus conditioning pre-processor is configured for generating meta data characterizing the plurality of stimuli, and wherein the neurome training processor is configured for logging the determined brain states of the user and the acquired meta data, and instructing the stimulus conditioning pre-processor to select or modify the at least one virtual source of content based on the logged determined brain states of the user and the acquired meta data.

### Claim 26 (depends on 20)

The system of claim 20, wherein the stimulus conditioning pre-processor is configured for modulating the analog instances of the plurality of stimuli, such that the modulated analog instances of the plurality of stimuli are peripherally input into the brain of the user.

### Claim 27 (depends on 19)

The system of claim 19, wherein the stimulus conditioning pre-processor is configured for generating meta data characterizing the plurality of stimuli, wherein the neurome comprises a plurality of brain state models, and the neurome training processor is configured for selecting one of the brain state models based on the generated meta data, and modifying the neurome by modifying the selected brain state model based on the plurality of determined brain states of the user and the plurality of determined brain states of the avatar.

### Claim 28 (depends on 1)

The system of claim 1, wherein the plurality of stimuli comprises a first plurality of different stimuli, and wherein the plurality of determined brain states of the avatar comprises a plurality of different determined brain states of the avatar.

### Claim 29 (depends on 28)

The system of claim 28, wherein the at least one source of content comprises a first plurality of different sources of content.

### Claim 30 (depends on 29)

The system of claim 29, wherein the first plurality of different sources of content are all in the same genre selected from one of a genre of movies, a genre of songs, a genre of books, a genre of household appliances, a genre of automobiles, a genre of foods, a genre of drinks, a genre of artwork, and sources of consumable chemical substances.

### Claim at position 31

31-114. (canceled)