US 2025/0094781 A1Published application

Multi-task gating for machine learning systems

AssigneeQUALCOMM Incorporated

InventorsBabak EHTESHAMI BEJNORDI, Gaurav KUMAR, Amelie Marie Estelle ROYER, Eduardo ESTEVES, Tijmen Pieter Frederik BLANKEVOORT, Mohsen GHAFOORIAN

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Systems and techniques are described herein for training and using multitask machine learning models. For example, a computing device can obtain training data for a first task in a layer in a neural network; perform, based on a determination from a first gating mechanism, the shared function on shared features of the training data using at least one shared channel to generate a shared feature map; perform, based on the determination from the first gating mechanism, the first task-specific function on first task-specific features of the training data using at least one first task-specific channel to generate a first task-specific feature map; generate an output for the first task-specific branch based on performing the shared function on the shared features and performing the first task-specific function on the first task-specific features; and update at least one parameter of the first gating mechanism based on the output.

Claims30

Dependent claims

An apparatus for training a neural network to perform at least one task, comprising:

at least one memory;
and
at least one processor coupled to the at least one memory, the at least one processor configured to:
obtain training data for a first task in a layer in a neural network, wherein the layer is associated with a first gating mechanism configured to determine whether to process shared features of the training data for the first task using a shared function of a shared branch or first task-specific features of the training data for the first task using a first task-specific function of a first task-specific branch, wherein the shared function is associated with one or more shared channels of the shared branch, and wherein the first task-specific function is associated with one or more first task-specific channels of the first task-specific branch;
perform, based on a determination from the first gating mechanism, the shared function on the shared features of the training data for the first task using at least one of the one or more shared channels to generate a shared feature map;
perform, based on the determination from the first gating mechanism, the first task-specific function on the first task-specific features of the training data for the first task using at least one of the one or more first task-specific channels to generate a first task-specific feature map;
generate an output for the first task-specific branch based on performing the shared function on the shared features of the training data and performing the first task-specific function on the first task-specific features of the training data;
and
update at least one parameter of the first gating mechanism based on the output.

6 more elements

An apparatus for performing at least one task, comprising:

at least one memory;
and
at least one processor coupled to the at least one memory, the at least one processor configured to:
receive input data for a first task in a layer in a neural network, wherein the layer is associated with a shared function of a shared branch and a first task-specific function of a first task-specific branch, and wherein the shared function is associated with one or more shared channels of the shared branch, and wherein the first task-specific function is associated with one or more first task-specific channels of the first task-specific branch;
perform the shared function on shared features of the input data for the first task using at least one of the one or more shared channels of the shared branch to generate a shared feature map;
perform the first task-specific function on first task-specific features of the input data using at least one of the one or more first task-specific channels associated with the first task-specific function to generate a first task-specific feature map;
and
generate an output for the first task-specific branch based on performing the shared function on the shared features of the input data and performing the first task-specific function on the first task-specific features of the input data.

5 more elements

A processor-implemented method for training a neural network to perform at least one task, comprising:

obtain training data for a first task in a layer in a neural network, wherein the layer is associated with a first gating mechanism configured to determine whether to process shared features of the training data for the first task using a shared function of a shared branch or first task-specific features of the training data for the first task using a first task-specific function of a first task-specific branch, wherein the shared function is associated with one or more shared channels of the shared branch, and wherein the first task-specific function is associated with one or more first task-specific channels of the first task-specific branch;
perform, based on a determination from the first gating mechanism, the shared function on the shared features of the training data for the first task using at least one of the one or more shared channels to generate a shared feature map;
perform, based on the determination from the first gating mechanism, the first task-specific function on the first task-specific features of the training data for the first task using at least one of the one or more first task-specific channels to generate a first task-specific feature map;
generate an output for the first task-specific branch based on performing the shared function on the shared features of the training data and performing the first task-specific function on the first task-specific features of the training data;
and
update at least one parameter of the first gating mechanism based on the output.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 18/468,873Filed 18 Sep 2023
Published: 20 Mar 2025
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

G06N 3/0455
Combinations of networks: auto-encoder networks; Encoder-decoder networks
G06N 3/0464
Architecture, e.g. interconnection topology: convolutional networks [CNN, ConvNet]
G06N 3/044
Architecture, e.g. interconnection topology: recurrent networks, e.g. Hopfield networks
G06N 3/084
Learning methods: backpropagation, e.g. using gradient descent

Family

No related US applications are recorded in the indexed filing history.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key