Recurrent neural network architecture search method and system based on an improved evolutionary algorithm, and medium

• Main Authors: WANG LEI, LI SHIMING, ZHANG HONGGUANG, TIAN SHUO, QU LIANHUA, HU KAI, GONG RUI, WANG SHUQUAN, XU WEIXIA, SHI WEI
• Format: Patent
• Language: Chinese; English
• Published: 12.05.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses a recurrent neural network architecture search method and system based on an improved evolutionary algorithm, and a medium. The method comprises the following steps: training aplurality of recurrent neural network sub-models to update a shared weight; initializing a generation population and a historical record table for recording the performance of all the recurrent neural network models; randomly sampling from the population to generate a sample, selecting a sample optimal model to perform mutation operation, removing the oldest or worst model in the population witha specified probability, and adding mutated child nodes into the population and the historical record table; and judging whether a preset ending condition is met or not, if not, continuing to carry out sample variation, and otherwise, outputting an optimal model in the historical record table. According to the method, the search process of a recurrent neural network architecture can be accelerated, the performance and the