# US 2026/0065155 A1 · Drift-based framework for lifelong learning of large ai systems

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

- Number: US 2026/0065155 A1
- Document ID: US20260065155A1
- Status: Published application
- Kind: A1
- Application number: 19/306,412
- Filed: 2025-08-21
- Published: 2026-03-05
- Earliest claimed: 2024-09-03
- Applicants: Regents of the University of Minnesota; President and Fellows of Harvard College
- Inventors: Jie Ding; Jin Du; Jia Liu
- Web page: https://patentgrep.com/patent/US20260065155A1

## CPC

- G06N 20/00: Machine learning
- G06F 18/241: relating to the classification model, e.g. parametric or non-parametric approaches
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A computer-implemented method includes receiving data and while using a process that promotes exploration during training, training a new set of model parameters using the received data. The new set of model parameters is used to form a collection of sets of model parameters. Data is separately applied to each set of model parameters in the collection to identify sets of model parameters that perform similarly on the set of data. The sets of model parameters that perform similarly on the data are grouped together in a group of sets of model parameters and test data is applied to groups of sets of model parameters to obtain an uncertainty measure for each group. A group with the lowest uncertainty measure is selected and outputs produced by the sets of model parameters in the selected group are used to generate an output value for the test data.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving data;
while using a process that promotes exploration during training, training a new set of model parameters using the received data;
placing the new set of model parameters in a collection of previous sets of model parameters to form a new collection of sets of model parameters;
applying a set of data separately to each set of model parameters in the new collection of sets of model parameters to identify sets of model parameters that perform similarly on the set of data;
grouping the sets of model parameters that perform similarly on the set of data together in a group of sets of model parameters;
applying test data to groups of sets of model parameters to obtain an uncertainty measure for each group;
selecting a group with the lowest uncertainty measure; and
using outputs produced by the sets of model parameters in the selected group to generate an output value for the test data.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1 wherein using a process that promotes exploration during training comprises adding noise to the received data.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1 wherein applying a set of data separately to each set of model parameters comprises applying a set of data used to train one of the previous sets of model parameters.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1 wherein training a new set of model parameters using the received data comprises updating a previous set of model parameters using the received data.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1 wherein each set of model parameters in the collection of sets of model parameters is trained using respective data associated with a respective unknown task.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5 wherein at least two of the sets of model parameters in the collection of sets of model parameters is trained using respective data associated with a same unknown task.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1 wherein using outputs produced by the sets of model parameters in the selected group to generate an output value comprises determining a mean of the outputs to generate the output value.

### Claim 8

A method of improving an artificial intelligence system so that the system performs well on a new task without forgetting how to perform an old task, the method comprising:
while using a process that promotes exploration during training, training a new set of model parameters using data for the new task;
grouping the new set of model parameters with prior sets of model parameters to form a group of sets of model parameters, wherein the grouping is based on similarities in performance between the new set of model parameters and the prior sets of model parameters; and
applying an input to each set of model parameters in the group of sets of model parameters to produce a set of outputs and using the set of outputs to determine a final output for the artificial intelligence system.

### Claim 9 (depends on 8)

The method of claim 8 wherein using a process that promotes exploration during training comprises adding noise to the data for the new task.

### Claim 10 (depends on 8)

The method of claim 8 wherein using a process that promotes exploration during training comprises adding noise to a prior set of model parameters to form a modified set of model parameters and updating the modified set of model parameters using the data for the new task to form the new set of model parameters.

### Claim 11 (depends on 8)

The method of claim 8 wherein using a process that promotes exploration during training comprises adding gradient noise when training the new set of model parameters.

### Claim 12 (depends on 8)

The method of claim 8 wherein the identity of the new task is unknown.

### Claim 13 (depends on 8)

The method of claim 8 further comprising forming a plurality of groups of sets of model parameters.

### Claim 14 (depends on 13)

The method of claim 13 further comprising selecting one group of the plurality of groups by applying the input to each set of model parameters in each group and determining which group provides a most-consistent output.

### Claim 15 (depends on 13)

The method of claim 13 wherein forming the plurality of groups of sets of model parameters comprises applying data used to form at least some of the sets of model parameters and forming the groups based on the outputs of the sets of model parameters.

### Claim 16

A system comprising:
a memory containing sets of model parameters;
a processor configured to perform steps comprising:
while using a process that promotes exploration during training, training a new set of model parameters using data;
grouping the new set of model parameters with prior sets of model parameters to form a group of sets of model parameters, wherein the grouping is based on similarities in performance between the new set of model parameters and the prior sets of model parameters; and
applying an input to each set of model parameters in the group of sets of model parameters to produce a set of outputs and using the set of outputs to determine a final output.

### Claim 17 (depends on 16)

The system of claim 16 wherein using a process that promotes exploration during training comprises adding noise to the data for the new task.

### Claim 18 (depends on 16)

The method of claim 16 wherein using a process that promotes exploration during training comprises adding gradient noise when training the new set of model parameters.

### Claim 19 (depends on 16)

The method of claim 16 further comprising forming a plurality of groups of sets of model parameters.

### Claim 20 (depends on 19)

The method of claim 19 further comprising selecting one group of the plurality of groups by applying the input to each set of model parameters in each group and determining which group provides a most-consistent output.
