Multi-objective neural architecture search framework
AssigneeSamsung Electronics Co., Ltd.
InventorsMostafa EL-KHAMY, Minsu CHO, Kee-Bong SONG
Life of this patent
Estimating the term…
Abstract
A system and a method are disclosed for performing a neural architecture search. The method includes sampling a discrete network search space a first time, determining a differential architecture network sampled from a super-network using continuous relaxation of the discrete network search space over operators in the super-network, calculating a reward based on a proxy accuracy or a proxy complexity of the differential architecture network, updating a distribution of the discrete network search space based on the reward, and determining an updated differential architecture network based on the reward.
Claims20
A method for performing a neural architecture search, comprising:
- sampling a discrete network search space a first time,
- determining a differential architecture network sampled from a super-network using continuous relaxation of the discrete network search space over operators in the super-network,
- calculating a reward based on a proxy accuracy or a proxy complexity of the differential architecture network,
- updating a distribution of the discrete network search space based on the reward, and
- determining an updated differential architecture network based on the reward.
An electronic device, comprising:
- at least one processor;
- and
- at least one memory operatively connected with the at least one processor, the at least one memory storing instructions, which when executed, instruct the at least one processor to perform a method of performing a neural architecture search by:
- sampling a discrete network search space a first time,
- determining a differential architecture network sampled from a super-network using continuous relaxation of the discrete network search space over operators in the super-network,
- calculating a reward based on a proxy accuracy or a proxy complexity of the differential architecture network,
- updating a distribution of the discrete network search space based on the reward, and
- determining an updated differential architecture network based on the reward.
Dependencies are inferred from the claim text.