# US 2024/0201957 A1 · Neural network model definition code generation and optimization

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

- Number: US 2024/0201957 A1
- Document ID: US20240201957A1
- Status: Published application
- Kind: A1
- Application number: 18/513,232
- Filed: 2023-11-17
- Published: 2024-06-20
- Earliest claimed: 2022-12-19
- Assignees: Micron Technology, Inc.
- Applicants: Micron Technology, Inc.
- Inventors: Abhishek Chaurasia; Andre Xian Ming Chang
- Web page: https://patentgrep.com/patent/US20240201957A1

## CPC

- G06F 8/34: Graphical or visual programming
- G06F 8/36: Software reuse
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system providing neural network model definition code generation and optimization is disclosed. The system receives inputs to facilitate the generation of an artificial intelligence model, such as freehand drawings of a model, modules available in repositories, various forms of content, and other inputs. The system utilizes a neural network to analyze the inputs and generates blocks and connections to generate a graph for the artificial intelligence model. Properties of the model are selected, and the system locates modules, generates code for modules, or both, based on the blocks and connections from the graph and the properties. The system generates the model definition for the artificial intelligence model using the located modules and the generated code. Once the model definition is completed, the artificial intelligence model may be utilized to perform a task for which the artificial intelligence model has been created to perform.

## Claims

### Claim 1

A system, comprising:
a memory; and
a processor, wherein the processor is configured to;
facilitate, by utilizing a neural network, selection of a plurality of modules for inclusion in an artificial intelligence model;
facilitate, by utilizing the neural network, selection of a property for each module of the plurality of modules for the artificial intelligence model;
establish, by utilizing the neural network, a connection between each module selected from the plurality of modules with at least one other module selected from the plurality of modules;
generate, by utilizing a neural network and based on the selection of the property for each module and the connection, a model definition for the artificial intelligence model by generating code for each module selected from the plurality of modules; and
execute a task by utilizing the artificial intelligence model via the model definition generated via the code for each module selected from the plurality of modules.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processor is further configured to update a parameter for at least one module of the plurality of modules of the artificial intelligence module after adding an additional module to or removing a module from the artificial intelligence model.

### Claim 3 (depends on 1)

The system of claim 1, wherein the processor is further configured to update an operation for at least one module of the plurality of modules of the artificial intelligence model after adding an additional module to or removing a module from the artificial intelligence model.

### Claim 4 (depends on 1)

The system of claim 1, wherein the processor is further configured to visually render a graph for the artificial intelligence model including a visual representation of each module of the plurality of modules selected for inclusion in the artificial intelligence model.

### Claim 5 (depends on 1)

The system of claim 1, wherein the plurality of modules are pre-defined modules, custom-generated modules, or a combination thereof.

### Claim 6 (depends on 1)

The system of claim 1, wherein the processor is further configured to identify at least one module of the plurality of modules of the artificial intelligence model for replacement.

### Claim 7 (depends on 6)

The system of claim 6, wherein the processor is further configured to conduct a neural architecture search in a plurality of repositories to identify at least one replacement module to replace the at least one module for replacement.

### Claim 8 (depends on 1)

The system of claim 1, wherein the processor is further configured to automatically modify the artificial intelligence model based on a change in the task.

### Claim 9 (depends on 1)

The system of claim 1, wherein the processor is further configured to receive a manually drawn artificial intelligence model comprising manually drawn modules.

### Claim 10 (depends on 9)

The system of claim 9, wherein the processor is further configured to extract text from each block in the manually drawn artificial intelligence model, and wherein the processor is further configured to identify at least one module from the plurality of modules correlating with the text.

### Claim 11 (depends on 10)

The system of claim 10, wherein the processor is further configured to generate a different model definition corresponding to the manually drawn artificial intelligence model and including the at least one module from the plurality of modules correlating with the text.

### Claim 12 (depends on 1)

The system of claim 1, wherein the processor is further configured to import the plurality of modules from a search space including a module collection.

### Claim 13

A method, comprising:
receiving, by utilizing a neural network, manually generated content serving as an input for generation of an artificial intelligence model;
extracting, by utilizing the neural network, text associated with the manually generated content;
detecting, by utilizing the neural network, a portion of the content within the manually generated content indicative of a visual representation of at least one module of the artificial intelligence model;
generating, by utilizing the neural network, a graph of the artificial intelligence model using the text and the portion of the content indicative of the visual representation of the artificial intelligence model; and
generating, by utilizing the neural network and based on the graph of the artificial intelligence model, a model definition for the artificial intelligence model by generating code for the artificial intelligence model; and
executing, by utilizing the neural network, the model definition for the artificial intelligence model to perform a task.

### Claim 14 (depends on 13)

The method of claim 13, further comprising generating the model definition for the artificial intelligence model by obtaining, via a neural architecture search, candidate modules for the artificial intelligence module from a repository.

### Claim 15 (depends on 13)

The method of claim 13, further comprising enabling selection of at least one property of the artificial intelligence model via an interface of an application associated with the neural network.

### Claim 16 (depends on 13)

The method of claim 13, further comprising displaying the code generated for the artificial intelligence model via a user interface.

### Claim 17 (depends on 13)

The method of claim 13, further comprising enabling selection of the at least one module of the artificial intelligence model for replacement by at least one other module.

### Claim 18 (depends on 13)

The method of claim 13, further comprising providing an option to adjust an intensity level for reducing operations or parameters associated with the artificial intelligence model.

### Claim 19 (depends on 13)

The method of claim 13, further comprising providing a digital canvas to enable drawing of blocks, connections, modules, or a combination thereof, associated with the artificial intelligence model.

### Claim 20

A device, comprising:
a memory; and
a processor;
wherein the processor is configured to identify, by utilizing a neural network, a task to be completed by an artificial intelligence model;
wherein the processor is configured to search, by utilizing the neural network, for a plurality of modules and content in a plurality of repositories;
wherein the processor is configured to extract, by utilizing the neural network, a portion of the content from the content that is associated with the task, the artificial intelligence model, or a combination thereof;
wherein the processor is configured to select, by utilizing the neural network, a set of candidate modules of the plurality of modules in the plurality of repositories based on a matching characteristics of the set of candidate modules with the task;
wherein the processor is configured to generate the artificial intelligence model based on the portion of the content and the set of candidate modules; and
wherein the processor is configured to execute the task using the artificial intelligence model.
