Method and system for optimizing deep learning models
AssigneeMediatek Inc.
InventorsTzu-Yun Chien, Bo-Yu Kuo, Jui-Yang Hsu, Kai-Ling Huang, Sheng-Je Hung
Life of this patent
Estimating the term…
Abstract
A method for optimizing deep learning models includes: initializing a plurality of pools, each including a plurality of candidate solutions; concurrently performing a plurality of tuning algorithms respectively within the plurality of pools during a single tuning run, thereby obtaining a plurality of selected candidate solutions; and generating an optimized model configuration based on the plurality of selected candidate solutions.
Claims23
A method for optimizing deep learning models, comprising:
- initializing a plurality of pools, each including a plurality of candidate solutions;
- concurrently performing a plurality of tuning algorithms respectively within the plurality of pools during a single tuning run, thereby obtaining a plurality of selected candidate solutions;
- and
- generating an optimized model configuration based on the plurality of selected candidate solutions.
A system for optimizing deep learning models, comprising:
- a processor;
- and
- a memory storing instructions that, when executed by the processor, cause the system to perform operations comprising:
- initializing a plurality of pools each including a plurality of candidate solutions;
- concurrently performing a plurality of tuning algorithms respectively within the plurality of pools during a single tuning run, thereby obtaining a plurality of selected candidate solutions;
- and
- generating an optimized model configuration based on the plurality of selected candidate solutions.
A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform operations of:
- initializing a plurality of pools, each including a plurality of candidate solutions;
- concurrently performing a plurality of tuning algorithms respectively within the plurality of pools during a single tuning run, thereby obtaining a plurality of selected candidate solutions;
- and
- generating an optimized model configuration based on the plurality of selected candidate solutions.
Dependencies are inferred from the claim text.