# US 2026/0030487 A1 · Optimization of deep learning algorithms for large digital data processing using evolutionary neural networks

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

- Number: US 2026/0030487 A1
- Document ID: US20260030487A1
- Status: Published application
- Kind: A1
- Application number: 19/181,522
- Filed: 2025-04-17
- Published: 2026-01-29
- Earliest claimed: 2024-07-24
- Assignees: Vmc Mar Com Inc.
- Applicants: VMC MAR COM Inc.
- Inventors: Mohammadreza NEHZATI
- Web page: https://patentgrep.com/patent/US20260030487A1

## CPC

- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/086: using evolutionary algorithms, e.g. genetic algorithms or genetic programming
- 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
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Embodiments of the present disclosure relate to neural networks for processing large digital datasets. Neural networks comprise both a convolutional neural network (CNN) and a recurrent neural network (RNN). The neural networks are optimized by applying genetic algorithms. Embedding vectors are processed by both the CNN and the RNN to produce a merged output.

## Claims

### Claim 1

A method comprising:
initializing a first plurality of neural networks;
determining performance metrics, each of the performance metrics corresponding to a respective neural network of the first plurality of neural networks,
wherein each of the performance metrics is based on accuracy of the respective neural network in evaluating training data;
selecting a subset of the first plurality of neural networks based on the performance metrics;
selecting a first neural network from the subset and a second neural network from the subset,
wherein the first neural network comprises a first convolutional neural network (CNN) and a first recurrent neural network (RNN), and
wherein the second neural network comprises a second CNN and a second RNN;
forming a third neural network, wherein forming the third neural network comprises (a) selecting weights of the first CNN, selecting weights of the second CNN, and forming a third CNN of the third neural network at least in part from the selected weights of the first CNN and the second CNN and (b) selecting weights of the first RNN, selecting weights of the second RNN, and forming a third RNN of the third neural network at least in part from the selected weights of the first RNN and the second RNN;
providing, to the third neural network, a plurality of embedding vectors generated from input data;
processing, by the third CNN, a first subset of the embedding vectors, thereby producing a first output of the third CNN, wherein the third RNN does not process the first output of the third CNN;
processing, by the third CNN, a second subset of the embedding vectors, thereby producing a second output of the third CNN;
processing, by the third RNN, the second output of the third CNN, thereby producing an output of the third RNN;
combining the first output of the third CNN with the output of the third RNN, thereby producing a merged output; and
classifying the input data based on the merged output.

### Claim at position 2

2-3. (canceled)

### Claim 4 (depends on 1)

The method of claim 1, wherein the first RNN comprises a first long short-term memory (LSTM) network, the second RNN comprises a second LSTM network, and the third RNN comprises a third LSTM network.

### Claim 5 (depends on 1)

The method of claim 1, wherein the input data comprises an electronic health record (EHR).

### Claim 6 (depends on 5)

The method of claim 5, wherein classifying the input data comprises generating at least one of the following: a patient treatment plan, a disease-progression prediction, or a disease-risk prediction.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
determining that a convergence criterion has been satisfied based at least in part on an accuracy of the classification of the input data.

### Claim 8 (depends on 1)

The method of claim 1, further comprising applying random variations to weights of the third neural network.

### Claim 9 (depends on 1)

The method of claim 1, wherein the training data comprises artificial electronic health records (EHRs) generated by combining elements of patient EHRs.

### Claim 10 (depends on 1)

The method of claim 1, wherein the first RNN comprises a first LSTM network and the second RNN comprises a second LSTM network.

### Claim 11 (depends on 10)

The method of claim 10, wherein the third neural network comprises a third CNN and a third LSTM network.

### Claim 12 (depends on 11)

The method of claim 11, wherein the third neural network is configured to provide an output of the third CNN to the third LSTM network.

### Claim 13 (depends on 11)

The method of claim 11, wherein each of the first CNN, the second CNN, and the third CNN is a respective two-dimensional CNN.

### Claim 14 (depends on 1)

The method of claim 1, wherein the first neural network and the second neural network are randomly selected from the subset.

### Claim 15

A system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to:
initialize a first plurality of neural networks;
determine performance metrics, each of the performance metrics corresponding to a respective neural network of the first plurality of neural networks,
wherein each of the performance metrics is based on accuracy of the respective neural network in evaluating training data;
select a subset of the first plurality of neural networks based on the performance metrics;
select a first neural network from the subset and a second neural network from the subset,
wherein the first neural network comprises a first convolutional neural network (CNN) and a first recurrent neural network (RNN), and
wherein the second neural network comprises a second CNN and a second RNN;
form a third neural network, wherein forming the third neural network comprises (a) selecting weights of the first CNN, selecting weights of the second CNN, and forming a third CNN of the third neural network at least in part from the selected weights of the first CNN and the second CNN and (b) selecting weights of the first RNN, selecting weights of the second RNN, and forming a third RNN of the third neural network at least in part from the selected weights of the first RNN and the second RNN;
provide, to the third neural network, a plurality of embedding vectors generated from input data;
process, by the third CNN, a first subset of the embedding vectors, thereby producing a first output of the third CNN, wherein the third RNN does not process the first output of the third CNN;
process, by the third CNN, a second subset of the embedding vectors, thereby producing a second output of the third CNN;
process, by the third RNN, the second output of the third CNN, thereby producing an output of the third RNN;
combine the first output of the third CNN with the output of the RNN, thereby producing a merged output; and
classify the input data based on the merged output.

### Claim at position 15

16-17. (canceled)

### Claim 18

A non-transitory computer readable medium having instructions thereon, the instructions, when executed by a computer, causing the computer to perform operations comprising:
initializing a first plurality of neural networks;
determining performance metrics, each of the performance metrics corresponding to a respective neural network of the first plurality of neural networks,
wherein each of the performance metrics is based on accuracy of the respective neural network in evaluating training data;
selecting a subset of the first plurality of neural networks based on the performance metrics;
selecting a first neural network from the subset and a second neural network from the subset,
wherein the first neural network comprises a first convolutional neural network (CNN) and a first recurrent neural network (RNN), and
wherein the second neural network comprises a second CNN and a second RNN; and
forming a third neural network, wherein forming the third neural network comprises (a) selecting weights of the first CNN, selecting weights of the second CNN, and forming a third CNN of the third neural network at least in part from the selected weights of the first CNN and the second CNN and (b) selecting weights of the first RNN, selecting weights of the second RNN, and forming a third RNN of the third neural network at least in part from the selected weights of the first RNN and the second RNN;
providing, to the third neural network, a plurality of embedding vectors generated from input data;
processing, by the third CNN, a first subset of the embedding vectors, thereby producing a first output of the third CNN, wherein the third RNN does not process the first output of the third CNN;
processing, by the third CNN, a second subset of the embedding vectors, thereby producing a second output of the third CNN;
processing, by the third RNN, the second output of the third CNN, thereby producing an output of the third RNN;
combining the first output of the third CNN with the output of the third RNN, thereby producing a merged output; and
classifying the input data based on the merged output.

### Claim at position 17

19-20. (canceled)

### Claim 21 (depends on 1)

The method of claim 1, wherein the merged output is based on a maximum of the first output of the third CNN and the output of the third RNN.

### Claim 22 (depends on 15)

The system of claim 15, wherein the merged output is based on a maximum of the first output of the third CNN and the output of the third RNN.

### Claim 23 (depends on 18)

The medium of claim 18, wherein the merged output is based on a maximum of the first output of the third CNN and the output of the third RNN.
