G2TT
来源类型Discussion paper
规范类型论文
来源IDDP14024
DP14024 Will Artificial Intelligence Replace Computational Economists Any Time Soon?
Serguei Maliar; Pablo Winant
发表日期2019-09-25
出版年2019
语种英语
摘要Artificial intelligence (AI) has impressive applications in many fields (speech recognition, computer vision, etc.). This paper demonstrates that AI can be also used to analyze complex and high-dimensional dynamic economic models. We show how to convert three fundamental objects of economic dynamics -- lifetime reward, Bellman equation and Euler equation -- into objective functions suitable for deep learning (DL). We introduce all-in-one integration technique that makes the stochastic gradient unbiased for the constructed objective functions. We show how to use neural networks to deal with multicollinearity and perform model reduction in Krusell and Smith's (1998) model in which decision functions depend on thousands of state variables -- we literally feed distributions into neural networks! In our examples, the DL method was reliable, accurate and linearly scalable. Our ubiquitous Python code, built with Dolo and Google TensorFlow platforms, is designed to accommodate a variety of models and applications.
主题Monetary Economics and Fluctuations
关键词Artificial intelligence Machine learning Deep learning Neural network Stochastic gradient Dynamic models Dynamic programming Bellman equation Euler equation Value function
URLhttps://cepr.org/publications/dp14024-1
来源智库Centre for Economic Policy Research (United Kingdom)
资源类型智库出版物
条目标识符http://119.78.100.153/handle/2XGU8XDN/542911
推荐引用方式
GB/T 7714
Serguei Maliar,Pablo Winant. DP14024 Will Artificial Intelligence Replace Computational Economists Any Time Soon?. 2019.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Serguei Maliar]的文章
[Pablo Winant]的文章
百度学术
百度学术中相似的文章
[Serguei Maliar]的文章
[Pablo Winant]的文章
必应学术
必应学术中相似的文章
[Serguei Maliar]的文章
[Pablo Winant]的文章
相关权益政策
暂无数据
收藏/分享

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。