PaperReading20200221
2024-09-07 00:33:47
CanChen
ggchen@mail.ustc.edu.cn
Busy...
Human-level concept learning through probabilistic program induction
- Motivation:After seeing only one example, human can generalize the example as a concept, distinguish the example from other examples which belong to different classes, and generate new examples from this class while deep learning models require lots of training data to finish the above tasks.
- Method: The paper uses the handwritten characters dataset and chooses primitives from the library as subparts and then they are used to form parts. Parts and relations make simple programs. Running the programs, we can new tokens.
- Contribution: This paper is a science paper, very rare in this field. In fact, I still do not understand some points in this paper but this paper did integrate into models the human learning process.
最新文章
- vmware下centos7桥接模式无法上网
- 基于Enterprise Library的Winform开发框架实现支持国产达梦数据库的扩展操作
- jquery对象和dom对象的相互转换
- Linux下python升级至2.7
- Volatile 说明
- 转载:C++之高精度算法
- Oracle除替换去掉换行符的方法
- awk完全手册
- MS SQL 事务日志管理小结
- Ubuntu宿主机与VMware中其他系统虚拟机的互通
- 煎蛋ooxx
- java 判断用户是PC端和还是APP端登陆
- 「POJ - 1003」Hangover
- java基础---->;Java的格式化输出
- [UE4]把枪打飞addImpulse
- ACM-ICPC 2018年北京网络赛 D-80 days
- Android Activity全面解析
- Linux发行版,分类,CentOS下载
- asp.net mvc5 下载文件方法
- Server Host Cannot be null解决方法
热门文章
- windows maven配置
- Centos610快照克隆后网络配置
- Codeforces Round #619 (Div. 2) B. Motarack's Birthday
- UI UED设计
- php对象、面向对象
- main函数递归
- 大数据篇:MapReduce
- .NET Runtime at IP 791F7E06 (79140000) with exit code 80131506.
- SQL查询效率注意事项 2011.12.27
- 吴裕雄 Bootstrap 前端框架开发——Bootstrap 显示代码:按键提示