Information processing apparatus, information processing method and non-transitory computer-readable storage medium
AssigneeCanon Kabushiki Kaisha
InventorYoshiki OHNO
Life of this patent
Estimating the term…
Abstract
An information processing apparatus comprises one or more memories storing instructions and one or more processors that execute the instructions to acquire, by a process for learning a plurality of tasks, an integration ratio of output of replacement layers for which a shared layer, which is shared by a plurality of tasks in a hierarchical neural network, is replaced by a neural network layer for each task, and acquire a learned parameter of the shared layer based on the acquired integration ratio and learned parameters of the replacement layers acquired by the process for learning.
Claims12
An information processing apparatus comprising one or more memories storing instructions and one or more processors that execute the instructions to:
- acquire, by a process for learning a plurality of tasks, an integration ratio of output of replacement layers for which a shared layer, which is shared by a plurality of tasks in a hierarchical neural network, is replaced by a neural network layer for each task;
- and
- acquire a learned parameter of the shared layer based on the acquired integration ratio and learned parameters of the replacement layers acquired by the process for learning.
An information processing apparatus comprising one or more memories storing instructions and one or more processors that execute the instructions to:
- acquire, by learning processing, an integration ratio for output of a unique layer that is unique to each task in a hierarchical neural network;
- and
- acquire a learned parameter of a layer that integrates two or more unique layers based on the acquired integration ratio and a learned parameter of the unique layers.
An information processing method performed by an information processing apparatus, the method comprising:
- acquiring, by a process for learning a plurality of tasks, an integration ratio of output of replacement layers for which a shared layer, which is shared by a plurality of tasks in a hierarchical neural network, is replaced by a neural network layer for each task;
- and
- acquiring a learned parameter of the shared layer based on the acquired integration ratio and learned parameters of the replacement layers acquired by the process for learning.
An information processing method performed by an information processing apparatus, the method comprising:
- acquiring, by learning processing, an integration ratio for output of a unique layer that is unique to each task in a hierarchical neural network;
- and
- acquiring a learned parameter of a layer that integrates two or more unique layers based on the acquired integration ratio and a learned parameter of the unique layers.
A non-transitory computer-readable storage medium storing a computer program for causing a computer to
- acquire, by a process for learning a plurality of tasks, an integration ratio of output of replacement layers for which a shared layer, which is shared by a plurality of tasks in a hierarchical neural network, is replaced by a neural network layer for each task;
- and
- acquire a learned parameter of the shared layer based on the acquired integration ratio and learned parameters of the replacement layers acquired by the process for learning.
A non-transitory computer-readable storage medium storing a computer program for causing a computer to
- acquire, by learning processing, an integration ratio for output of a unique layer that is unique to each task in a hierarchical neural network;
- and
- acquire a learned parameter of a layer that integrates two or more unique layers based on the acquired integration ratio and a learned parameter of the unique layers.
Dependencies are inferred from the claim text.