# US 2023/0267380 A1 · Methods, systems, and computer readable media for machine learning of multiple tasks

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

- Number: US 2023/0267380 A1
- Document ID: US20230267380A1
- Status: Published application
- Kind: A1
- Application number: 18/112,763
- Filed: 2023-02-22
- Published: 2023-08-24
- Earliest claimed: 2022-02-22
- Applicants: The Trustees of the University of Pennsylvania
- Inventors: Pratik Anil Chaudhari; Rahul Ramesh
- Web page: https://patentgrep.com/patent/US20230267380A1

## CPC

- G06N 3/045: Combinations of networks
- G06N 20/20: Ensemble learning
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods, systems, and computer readable media for machine learning of multiple tasks. In some examples, a method includes performing multiple rounds of training. For each training round, the method includes selecting a subset of computing tasks from the tasks being learned; building a feature generator for the subset of computing tasks; and training a task-specific classifier for each computing task, resulting in model for each computing task of the subset of computing tasks. The method can then include using the models for performing one of the computing tasks.

## Claims

### Claim 1

A method for machine learning, the method comprising:
for each training round of a plurality of training rounds:
selecting a subset of computing tasks from a plurality of computing tasks;
building a feature generator for the subset of computing tasks; and
training a task-specific classifier for each computing task of the subset of computing tasks, resulting in a model for each computing task of the subset of computing tasks; and
performing, using at least some of the models for the computing tasks, one of the computing tasks.

### Claim 2 (depends on 1)

The method of claim 1, wherein selecting the subset of computing tasks comprises maintaining a vector of task-specific weights and selecting the subset of computing tasks based on the task-specific weights.

### Claim 3 (depends on 2)

The method of claim 2, wherein selecting the subset of computing tasks based on the task-specific weights comprises drawing the subset of computing tasks from a multinomial distribution of the task-specific weights.

### Claim 4 (depends on 1)

The method of claim 1, further comprising revisiting at least a first computing task from the plurality of computing tasks by adding one or more new models.

### Claim 5 (depends on 4)

The method of claim 4, further comprising maintaining one or more models from previous training rounds not updated in successive training rounds.

### Claim 6 (depends on 1)

The method of claim 1, wherein each of the plurality of computing tasks shares a common input domain.

### Claim 7 (depends on 1)

The method of claim 1, comprising learning at least one task-specific adapter for at least one computing task having a different input domain from at least one other computing task.

### Claim 8

A system for machine learning, the system comprising:
at least one processor, and
a multi-task learner implemented on the at least one processor and configured to perform operations comprising:
for each training round of a plurality of training rounds:
selecting a subset of computing tasks from a plurality of computing tasks;
building a feature generator for the subset of computing tasks; and
training a task-specific classifier for each computing task of the subset of computing tasks, resulting in a model for each computing task of the subset of computing tasks; and
performing, using at least some of the models for the computing tasks, one of the computing tasks.

### Claim 9 (depends on 8)

The system of claim 8, wherein selecting the subset of computing tasks comprises maintaining a vector of task-specific weights and selecting the subset of computing tasks based on the task-specific weights.

### Claim 10 (depends on 9)

The system of claim 9, wherein selecting the subset of computing tasks based on the task-specific weights comprises drawing the subset of computing tasks from a multinomial distribution of the task-specific weights.

### Claim 11 (depends on 8)

The system of claim 8, further comprising revisiting at least a first computing task from the plurality of computing tasks by adding one or more new models.

### Claim 12 (depends on 11)

The system of claim 11, further comprising maintaining one or more models from previous training rounds not updated in successive training rounds.

### Claim 13 (depends on 8)

The system of claim 8, wherein each of the plurality of computing tasks shares a common input domain.

### Claim 14 (depends on 8)

The system of claim 8, comprising learning at least one task-specific adapter for at least one computing task having a different input domain from at least one other computing task.

### Claim 15

A non-transitory computer readable medium storing executable instructions that when executed by at least one processor of a computer control the computer to perform operations comprising:
for each training round of a plurality of training rounds:
selecting a subset of computing tasks from a plurality of computing tasks;
building a feature generator for the subset of computing tasks; and
training a task-specific classifier for each computing task of the subset of computing tasks, resulting in a model for each computing task of the subset of computing tasks; and
performing, using at least some of the models for the computing tasks, one of the computing tasks.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein selecting the subset of computing tasks comprises maintaining a vector of task-specific weights and selecting the subset of computing tasks based on the task-specific weights.

### Claim 17 (depends on 16)

The non-transitory computer readable medium of claim 16, wherein selecting the subset of computing tasks based on the task-specific weights comprises drawing the subset of computing tasks from a multinomial distribution of the task-specific weights.

### Claim 18 (depends on 15)

The non-transitory computer readable medium of claim 15, the operations further comprising revisiting at least a first computing task from the plurality of computing tasks by adding one or more new models.

### Claim 19 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein each of the plurality of computing tasks shares a common input domain.

### Claim 20 (depends on 15)

The non-transitory computer readable medium of claim 15, the operations further comprising learning at least one task-specific adapter for at least one computing task having a different input domain from at least one other computing task.
