# US 2021/0334657 A1 · Cognitive computing methods and systems based on bilogival neurol networks

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

- Number: US 2021/0334657 A1
- Document ID: US20210334657A1
- Status: Published application
- Kind: A1
- Application number: 17/274,020
- Filed: 2019-09-08
- Published: 2021-10-28
- Earliest claimed: 2018-09-08
- Assignees: Alpvision S.A.
- Applicants: Alpvision S.A.
- Inventors: Frederic JORDAN; Martin KUTTER; Yves DELACRETAZ
- Web page: https://patentgrep.com/patent/US20210334657A1

## CPC

- G06N 3/08: Learning methods
- G06N 3/002: {Biomolecular computers, i.e. using biomolecules, proteins, cells (using DNA G06N3/123; using neurons G06N3/061)}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/061: {using biological neurons, e.g. biological neurons connected to an integrated circuit}
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A Biological Neural Network (BNN) core unit comprising a neural cell culture, an input stimulation unit, an output readout unit may be controlled through its various life cycles to provide data processing functionality. An automation system comprising an environmental and chemical controller unit adapted to operate with the BNN stimulation and readout data interfaces facilitates the monitoring and adaptation of the BNN core unit parameters. Pre-processing and post-processing of the BNN interface signals may further facilitate the training and reinforcement learning by the BNN. Multiple BNN core units may also be assembled together as a stack. The proposed system provides a BNN Operating System as a core component for a wetware server to receive, process and transmit data for different client applications without exposing the BNN core unit components to the client user while requiring significantly less energy than conventional silicon-based hardware and software information processing for high-level cognitive computing tasks.

## Claims

### Claim 1

An automated processing system for transforming a spatio-temporal input data signal into a spatio-temporal output data signal, the system comprising:
an in vitro biological neural network (BNN) culture of neural cells in a BNN core unit;
an input stimulation unit adapted to apply an input spatio-temporal stimulation signal into a first set of the neural cells;
an output readout unit adapted to capture an output spatio-temporal readout signal from a second set of the neural cells;
one or more nutrient tanks in connection with one or more nutrient dispensers to inject one or more nutrients into the BNN culture;
one or more additive tanks each in connection with one or more additive dispensers to inject one or more additives into the BNN culture;
one or more nutrient waste collectors, for filtering and expelling nutrient waste from the BNN culture;
one or more additive waste collectors, for filtering and expelling additive waste from the BNN culture;
one or more vascularization networks to connect said nutrient dispensers, additive dispensers, nutrient waste collectors and additive waste collectors to the BNN culture;
one or more sensors to measure at least one environmental parameter of the BNN culture; and
an automation controller configured to adapt the stimulation signal to the input data signal, to adapt the output data signal to the readout signal and to control at least one of:
a BNN core unit environmental parameter;
a BNN culture nutrient supply;
a BNN culture additive supply;
a BNN culture nutrient waste collection;
a BNN culture additive waste collection;
to maintain the homeostasis of the BNN culture over time so that the spatio-temporal input data signal is continuously transformed into the spatio-temporal output data signal.

### Claim 2 (depends on 1)

The automated processing system of claim 1, wherein the nutrients are chosen among amino acids, carbohydrates, vitamins and minerals or a combination thereof.

### Claim 3 (depends on 1)

The automated processing system of claim 1, wherein the additives are chosen among a dopaminergic stimulation enhancer to increase the dopaminergic response of the BNN, a dopaminergic stimulation inhibitor to decrease the dopaminergic response of the BNN, botox, nicotine, curare, amphetamine, cocaine, MDMA, strychnine, THC, caffeine, benzodiazepines, barbiturates, alcohol, opiates, growth factors, hormone, a gaz, or a combination thereof.

### Claim 4 (depends on 1)

The automated processing system of claim 1, wherein the vascularization network is manufactured using 3D bioprinting using a biocompatible material.

### Claim 5 (depends on 1)

The automated processing system claim 1, wherein the vascularization network is grown from stem cells on the BNN culture support.

### Claim 6 (depends on 1)

The automated processing system of claim 1, wherein the vascularization network is a soft and compressible, porous and absorbent material forming a 3D structure suitable to mechanically host the BNN cells in its pores while adjusting to their growth development as a 3D cell culture.

### Claim 7 (depends on 1)

The automated processing system of claim 1, wherein the sensor measures the temperature, the hygrometry, the pH or the CO2 environmental parameter of the BNN culture.

### Claim 8 (depends on 1)

The automated processing system of claim 1, wherein the automation controller further comprises a pre-processing unit to transform, with at least one of a spatio-temporal signal filter, a spatio-temporal signal classifier, a machine learning algorithm based on a mathematical or statistical model, an artificial neural network, a convolutional neural network, a support vector machine classifier, a random forest classifier, a genetic algorithm, a genetic programming algorithm, or a reservoir computing method, the input data signal into the stimulation signal.

### Claim 9 (depends on 1)

The automated processing system of claim 1, wherein the automation controller further comprises a post-processing unit to transform with at least one of a spatio-temporal signal filter, a spatio-temporal signal classifier, a machine learning algorithm based on a mathematical or statistical model, an artificial neural network, a convolutional neural network, a support vector machine classifier, a random forest classifier, a genetic algorithm, a genetic programming algorithm, or a reservoir computing method, the readout signal into the output data signal.

### Claim 10 (depends on 1)

The automated processing system of claim 1, further adapted to control a stack of BNN core units, the first part of the BNN culture being in a first BNN core unit from said stack and the second part of the BNN culture being in a second BNN core unit from said stack.

### Claim 11 (depends on 1)

A server for executing automated processing tasks, the server comprising the automated processing system of claim 1.

### Claim 12

A method for transforming a spatio-temporal input data signal into a spatio-temporal output data signal with an automation controller and a Biological Neural Network (BNN) core unit, the BNN core unit comprising at least an in vitro culture of neural cells (the BNN culture) adapted, with an input stimulation unit, to feed a stimulation spatio-temporal signal into a first set of the neural cells and adapted, with an output readout unit, to readout a spatio-temporal signal from a second set of the neural cells, the method comprising:
pre-processing, with the automation controller, the spatio-temporal input data signal into the stimulation spatio-temporal signal;
post-processing, with the automation controller, the readout spatio-temporal signal into the spatio-temporal output data signal; and
controlling, with the automation controller, at least one of:
a BNN core unit environmental parameter;
a BNN culture nutrient supply;
a BNN culture additive supply;
a BNN culture nutrient waste collection;
a BNN culture additive waste collections;
a pre-processing parameter;
a post-processing parameter;
to maintain the homeostasis of the BNN neural cell culture over time so that the BNN core unit continuously transforms the spatio-temporal input data signal into the spatio-temporal output data signal.

### Claim 13 (depends on 12)

The method of claim 12, further comprising
receiving a target spatio-temporal output data signal;
adapting at least one of:
the BNN core unit environmental parameters;
the BNN culture nutrient supply;
the BNN culture additive supply;
the BNN culture nutrient waste collection;
the BNN culture additive waste collection;
a pre-processing parameter;
a post-processing parameter;
to minimize the error between the output spatio-temporal data signal and the target spatio-temporal output data signal.

### Claim 14 (depends on 12)

The method of claim 12, wherein pre-processing comprises transforming, with at least one of a spatio-temporal signal filter, a spatio-temporal signal classifier, a machine learning algorithm based on a mathematical or statistical model, an artificial neural network, a convolutional neural network, a support vector machine classifier, a random forest classifier, a genetic algorithm, a genetic programming algorithm, a reservoir computing method, the spatio-temporal input data signal into the stimulation spatio-temporal signal.

### Claim 15 (depends on 12)

The method of claim 12, wherein post-processing comprises transforming, with at least one of a spatio-temporal signal filter, a spatio-temporal signal classifier, a machine learning algorithm based on a mathematical or statistical model, an artificial neural network, a convolutional neural network, a support vector machine classifier, a random forest classifier, a genetic algorithm, a genetic programming algorithm, a reservoir computing method, the readout spatio-temporal signal into the spatio-temporal output data signal.