To expand the difference between the offspring population and the parental population generated using genetic algo-rithm,a search algorithm,called wide single-path architecture search algorithm,was proposed.The method divided the search process into two stages.In the first stage,a new crossover operator and the stagnation detection algorithm were used to increase the gap between the offspring population and the parental population,and the search scope was expanded.The second stage was contraction,in which several individuals obtained in the previous stage were used and the single-point crossover was used to search,ensuring the stability of the search and obtaining the final result.Experimental results on four datasets show that the optimal network searched using the proposed algorithm can obtain competitive results compared with hand-designed neural net-works and neural architecture search methods based on traditional genetic algorithm.
维普
万方数据