CNN Optimization with a Genetic Algorithm

2019 IEEE National Aerospace and Electronics Conference (NAECON)(2019)

引用 4|浏览16
暂无评分
摘要
Hand tuning convolutional neural networks (CNN) for performance optimization can be tedious. A novel approach using a genetic algorithm to automate CNN hyper-parameter adjustment is proposed. This automated approach shows a 5% accuracy improvement over hand tuned methods and highly energy efficient networks on the Intel Movidius Compute Stick.
更多
查看译文
关键词
energy efficient networks,hand tuned methods,accuracy improvement,automated approach,CNN hyper-parameter adjustment,performance optimization,convolutional neural networks,hand tuning,genetic algorithm,CNN optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要