US 11,914,672 B2
Method of neural architecture search using continuous action reinforcement learning
Mohammad Salameh, Edmonton (CA); Keith George Mills, Leduc (CA); and Di Niu, Edmonton (CA)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by Mohammad Salameh, Edmonton (CA); Keith George Mills, Leduc (CA); and Di Niu, Edmonton (CA)
Filed on Sep. 29, 2021, as Appl. No. 17/488,796.
Prior Publication US 2023/0096654 A1, Mar. 30, 2023
Int. Cl. G06F 18/214 (2023.01); G06N 3/04 (2023.01); G06F 18/21 (2023.01)
CPC G06F 18/214 (2023.01) [G06F 18/217 (2023.01); G06N 3/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for neural architectural search (NAS) for performing a task, the method comprising:
(i) generating, by an actor neural network having actor parameters in accordance with current values of the actor parameters, a set of continuous neural network architecture parameters comprising score distributions over possible values for configuring a plurality of architecture cells of a trained search space;
(ii) discretizing the set of continuous architecture parameters into a set of discrete neural network architecture parameters;
(iii) generating a candidate architecture by configuring the trained search space using the discrete neural network architecture parameters, which specify a subset of the plurality of architecture cells to be active;
(iv) evaluating a performance of the candidate architecture at performing the task;
(v) determining a reward and a state for the discrete neural network architecture parameters based on the performance;
(vi) storing an experience tuple comprising the continuous neural network architecture parameters, the reward, and the state in a buffer storage;
(vii) learning a mapping, by a critic neural network, between network architectures and performance; and
(viii) updating the actor neural network with the learned mapping from the critic neural network.