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
- Atcoder beginer contest 258 [competition record]
- LeetCode 6004. Get operands of 0
- MySql——CRUD
- Data analysis thinking analysis methods and business knowledge - analysis methods (III)
- How to solve the problems caused by the import process of ecology9.0
- LeetCode 斐波那契序列
- 剖面测量之提取剖面数据
- Spark AQE
- MySQL之函数
- JS can really prohibit constant modification this time!
猜你喜欢

关于slmgr命令的那些事

Spark SQL null value, Nan judgment and processing

Idea远程提交spark任务到yarn集群

Wechat applet -- wxml template syntax (with notes)

Go learning - dependency injection

FFT learning notes (I think it is detailed)

Comment faire votre propre robot

LeetCode 1189. Maximum number of "balloons"

Set data real-time update during MDK debug

Classic CTF topic about FTP protocol
随机推荐
Power Query数据格式的转换、拆分合并提取、删除重复项、删除错误、转置与反转、透视和逆透视
NSSA area where OSPF is configured for Huawei equipment
NLP basic task word segmentation third party Library: ICTCLAS [the third party library with the highest accuracy of Chinese word segmentation] [Chinese Academy of Sciences] [charge]
如何制作自己的機器人
[noi simulation] Anaid's tree (Mobius inversion, exponential generating function, Ehrlich sieve, virtual tree)
Teach you to run uni app with simulator on hbuilderx, conscience teaching!!!
NLP generation model 2017: Why are those in transformer
XML Configuration File
About the slmgr command
Ffmpeg captures RTSP images for image analysis
Solve the problem of reading Chinese garbled code in sqlserver connection database
多线程与高并发(8)—— 从CountDownLatch总结AQS共享锁(三周年打卡)
Natural language processing (NLP) - third party Library (Toolkit):allenlp [library for building various NLP models; based on pytorch]
Go learning --- read INI file
[QT] QT uses qjson to generate JSON files and save them
Spark AQE
Search (DFS and BFS)
【DesignMode】组合模式(composite mode)
LeetCode 斐波那契序列
Key structure of ffmpeg - avframe