当前位置:网站首页>MIT博士论文 | 使用神经符号学习的鲁棒可靠智能系统
MIT博士论文 | 使用神经符号学习的鲁棒可靠智能系统
2022-07-06 00:33:00 【智源社区】

这篇论文表明,通过神经符号模型的视角来看待智能系统比传统的深度学习方法有几个好处。神经符号模型包含符号程序性构造,如循环、条件和连续的神经成分。符号部分使模型具有可解释性、泛化性和稳健性,而神经部分处理智能系统的复杂性。具体而言,本文提出了两类神经符号模型——状态机和神经符号transformers,并以基于强化学习的自主系统和多机器人系统为例对它们进行了评估。这些案例研究表明,学习的神经符号模型是人类可读的,可以外推到看不见的场景,并可以处理规范中的稳健目标。为了有效地学习这些神经符号模型,我们引入了利用机器学习和程序合成的最新技术的神经符号学习算法。
边栏推荐
- Go learning - dependency injection
- An understanding of & array names
- Global and Chinese markets for hinged watertight doors 2022-2028: Research Report on technology, participants, trends, market size and share
- Go learning --- read INI file
- MySQL storage engine
- XML Configuration File
- Browser reflow and redraw
- Room cannot create an SQLite connection to verify the queries
- 常用API类及异常体系
- Set data real-time update during MDK debug
猜你喜欢
随机推荐
[Chongqing Guangdong education] reference materials for Zhengzhou Vocational College of finance, taxation and finance to play around the E-era
Permission problem: source bash_ profile permission denied
Shardingsphere source code analysis
Key structure of ffmpeg - avframe
Recognize the small experiment of extracting and displaying Mel spectrum (observe the difference between different y_axis and x_axis)
认识提取与显示梅尔谱图的小实验(观察不同y_axis和x_axis的区别)
Set data real-time update during MDK debug
Natural language processing (NLP) - third party Library (Toolkit):allenlp [library for building various NLP models; based on pytorch]
Arduino六足机器人
Huawei equipment is configured with OSPF and BFD linkage
OpenCV经典100题
多线程与高并发(8)—— 从CountDownLatch总结AQS共享锁(三周年打卡)
Model analysis of establishment time and holding time
Pointer - character pointer
Key structure of ffmpeg -- AVCodecContext
NSSA area where OSPF is configured for Huawei equipment
Uniapp development, packaged as H5 and deployed to the server
Pointer pointer array, array pointer
Mysql - CRUD
wx. Getlocation (object object) application method, latest version









