Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hscspring/ai-methods
Kinds of Methods in AI.
https://github.com/hscspring/ai-methods
Last synced: about 1 month ago
JSON representation
Kinds of Methods in AI.
- Host: GitHub
- URL: https://github.com/hscspring/ai-methods
- Owner: hscspring
- License: mit
- Created: 2018-01-07T11:20:40.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2020-09-25T02:45:46.000Z (about 4 years ago)
- Last Synced: 2024-10-02T13:50:35.350Z (about 1 month ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 52.1 MB
- Stars: 6
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# GeneralAI
一直对 AI 情有独钟，学习算法半年有余，感觉各方面知识过于庞杂：机器学习、深度学习、强化学习、GAN、传统算法……数不胜数，故决定构建自己的 AI 算法体系。
恰好看到 [MIT 的人工智能课程](http://open.163.com/movie/2017/9/Q/S/MCTMNN3UI_MCTMNR8QS.html)，看了课程介绍觉得欲罢不能，决定就从这里开始。
## AI 简史
- 1842: Lady Lovelace, First programmer
- 1950: Turing, Turing Test Paper
- 1960: Marvin Minsky, 《Steps toward Aitificial Intelligence》
- 1970-2000:
- early DAWN age
- James Slagle, a program did symbolic integration（积分程序）
- Another: Eliza
- Another: analogy
- Late dawn
- vision
- learning
- expert systems: Bizs, Deep Blue
- BULLDOZER time
## What Is AI?
- THINKING, PERCEPTION, ACTION: LOOPS TOGETHER
- MODELS TARGETED AT
- REPRESENTATIONS THAT SUPPORT
- CONSTRAINTS EXPOSED BY
- ALGORITHMS ENABLED BY
### GENERATE AND TEST
- Generating some possible solutions
- feeding them into a box that test them
- out the other side comes mostly failures, but every once in a while we get something that succeeds and pleases us.
### Rumpelstiltskin principal
once you can name something, you get power over it.
### Lauguage
Lauguage is at the center of thins because oit enables storytelling going up, and marshaling the resources of the perceptual apparatus that are lying down.
语言处在一切的中心，它向上让故事讲述成为可能，并向下统御感觉系统的各种资源。
## Sources
- [deepmind/learning-to-learn: Learning to Learn in TensorFlow](https://github.com/deepmind/learning-to-learn)
- [An Explicitly Relational Neural Network Architecture](https://arxiv.org/pdf/1905.10307.pdf)