摘要
人工神经网络具有很强的自学习能力,善于联想、概括、类比和推理,能从大量统计资料中分析提取宏观统计规律,同时具有很强的鲁棒性、容错性以及强大并行计算能力,是进行非传统建模的有效工具。目前,应用比较多的BP神经网络,可通过学习以任意精度逼近任何连续映射,在农业工程项目中展示出了广阔的应用前景。主要介绍了人工神经网络的原理、特点及其在玉米气候适宜性评价中的应用。
Artificial neural network is an effective non-traditional modeling tool with a strong self-learning ability. It' s good at not only thinking, summarizing, analogizing, reasoning, but also analyzing and extracting the law of macrostatistics from a large number of statistical data. At the same time, it also has a strong robustness, fault tolerance as well as formidable parallel computing ability. At present, BP neural net- Work applied most can approach any continuous mapping through the study of the random precision and demonstrate a broad application prospects in agricultural projects. The principles and characteristics of artificial neural networks and the applications in the climate suitability evaluation of maize were mainly introduced.
出处
《安徽农业科学》
CAS
北大核心
2009年第35期17793-17794,共2页
Journal of Anhui Agricultural Sciences
关键词
人工神经网络
玉米
气候适宜性
Artificial neural network
Maize
Climatic suitability