“第十二章 机器学习基本流程”版本间的差异
来自cslt Wiki
(→高级读者) |
|||
(相同用户的10个中间修订版本未显示) | |||
第2行: | 第2行: | ||
*[[教学参考-12|教学参考]] | *[[教学参考-12|教学参考]] | ||
*[http://aigraph.cslt.org/courses/12/course-12.pptx 课件] | *[http://aigraph.cslt.org/courses/12/course-12.pptx 课件] | ||
− | * | + | *小清爱提问:什么是是梯度下降算法?[http://aigraph.cslt.org/courses/12/12-1.什么是梯度下降算法?.mp4] |
*小清爱提问:什么是模拟退火算法?[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247486965&idx=1&sn=30da3c422773f7cb530eb6047d91b30e&chksm=c3080737f47f8e21802ca8650d8a39d434102f09ef9693b8041f4c24f8888f7d5c1c5a6fc05c&scene=178#rd] | *小清爱提问:什么是模拟退火算法?[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247486965&idx=1&sn=30da3c422773f7cb530eb6047d91b30e&chksm=c3080737f47f8e21802ca8650d8a39d434102f09ef9693b8041f4c24f8888f7d5c1c5a6fc05c&scene=178#rd] | ||
*小清爱提问:什么是奥卡姆剃刀准则? [https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247486241&idx=1&sn=328b83f1c63103ffff86b1d38c3ac048&chksm=c30801e3f47f88f539f0e68f4cfc5a1e8a46e861ea0f2c732ed370530c4996e40b49a2ee6da6&scene=178#rd] | *小清爱提问:什么是奥卡姆剃刀准则? [https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247486241&idx=1&sn=328b83f1c63103ffff86b1d38c3ac048&chksm=c30801e3f47f88f539f0e68f4cfc5a1e8a46e861ea0f2c732ed370530c4996e40b49a2ee6da6&scene=178#rd] | ||
*小清爱提问:为什么说数据是人工智能的粮食?[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247485586&idx=1&sn=1892fe37396e19e57b1728604402e186&chksm=c3080250f47f8b46a9b96f88739e3c698b89fd24d90c1b2cad41fa9a3fb4956abc5306a5c7b5&scene=178#rd] | *小清爱提问:为什么说数据是人工智能的粮食?[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247485586&idx=1&sn=1892fe37396e19e57b1728604402e186&chksm=c3080250f47f8b46a9b96f88739e3c698b89fd24d90c1b2cad41fa9a3fb4956abc5306a5c7b5&scene=178#rd] | ||
− | |||
− | |||
==扩展阅读== | ==扩展阅读== | ||
第15行: | 第13行: | ||
* 百度百科:梯度下降法[https://baike.baidu.com/item/%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D/4864937][http://baike.baidu.com/l/FdY9mFXE] | * 百度百科:梯度下降法[https://baike.baidu.com/item/%E6%A2%AF%E5%BA%A6%E4%B8%8B%E9%99%8D/4864937][http://baike.baidu.com/l/FdY9mFXE] | ||
* 知乎:梯度下降法[https://zhuanlan.zhihu.com/p/36902908] | * 知乎:梯度下降法[https://zhuanlan.zhihu.com/p/36902908] | ||
− | * 维基百科:模拟退火算法 [http://aigraph.cslt.org/courses/12/ | + | * 知乎:小批量梯度下降法[https://zhuanlan.zhihu.com/p/72929546] |
+ | * 知乎:动量梯度下降法[https://www.jiqizhixin.com/graph/technologies/d6ee5e5b-43ff-4c41-87ff-f34c234d0e32][] | ||
+ | * 维基百科:模拟退火算法 [http://aigraph.cslt.org/courses/12/模拟退火.pdf][http://aigraph.cslt.org/courses/12/Simulated_annealing.pdf] | ||
* 百度百科:模拟退火算法[https://baike.baidu.com/item/%E6%A8%A1%E6%8B%9F%E9%80%80%E7%81%AB%E7%AE%97%E6%B3%95/355508][http://baike.baidu.com/l/Smyp3NfN] | * 百度百科:模拟退火算法[https://baike.baidu.com/item/%E6%A8%A1%E6%8B%9F%E9%80%80%E7%81%AB%E7%AE%97%E6%B3%95/355508][http://baike.baidu.com/l/Smyp3NfN] | ||
* 知乎:模拟退火详解 [https://zhuanlan.zhihu.com/p/266874840] | * 知乎:模拟退火详解 [https://zhuanlan.zhihu.com/p/266874840] | ||
第21行: | 第21行: | ||
* 维基百科:奥卡姆剃刀[http://aigraph.cslt.org/courses/12/奥卡姆剃刀.pdf][http://aigraph.cslt.org/courses/12/Occam's_razor.pdf] | * 维基百科:奥卡姆剃刀[http://aigraph.cslt.org/courses/12/奥卡姆剃刀.pdf][http://aigraph.cslt.org/courses/12/Occam's_razor.pdf] | ||
* 百度百科:奥卡姆剃刀[https://baike.baidu.com/item/%E5%A5%A5%E5%8D%A1%E5%A7%86%E5%89%83%E5%88%80%E5%8E%9F%E7%90%86/10900565][http://baike.baidu.com/l/HUkXrXzT] | * 百度百科:奥卡姆剃刀[https://baike.baidu.com/item/%E5%A5%A5%E5%8D%A1%E5%A7%86%E5%89%83%E5%88%80%E5%8E%9F%E7%90%86/10900565][http://baike.baidu.com/l/HUkXrXzT] | ||
+ | * 维基百科:过拟合[http://aigraph.cslt.org/courses/12/Overfitting.pdf][http://aigraph.cslt.org/courses/12/過適.pdf] | ||
+ | * 维基百科:GPT-3 [http://aigraph.cslt.org/courses/12/GPT-3-zh.pdf][http://aigraph.cslt.org/courses/12/GPT-3-en.pdf] | ||
+ | * 机器之心:当谈论机器学习中的公平公正时,我们该谈论些什么?[https://www.jiqizhixin.com/articles/2020-06-03-11] | ||
+ | * 机器之心:数据增强 [https://www.jiqizhixin.com/articles/2019-12-04-10] | ||
+ | * 知乎:数据增强 [https://zhuanlan.zhihu.com/p/38345420][https://zhuanlan.zhihu.com/p/41679153] | ||
+ | * 什么是模型预训练[https://paddlepedia.readthedocs.io/en/latest/tutorials/pretrain_model/pretrain_model_description.html] | ||
+ | * 迁移学习 [https://baike.baidu.com/item/%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0/22768151] | ||
+ | |||
+ | ==视频展示== | ||
+ | |||
+ | * 奥卡姆剃刀 [https://www.bilibili.com/video/BV1j54y117eT?spm_id_from=333.337.search-card.all.click] | ||
+ | * 为你读书 || 你必须了解的四个概念之二:奥卡姆剃刀原理 [https://www.bilibili.com/video/BV1PS4y1D7Cb?spm_id_from=333.337.search-card.all.click] | ||
第27行: | 第39行: | ||
* 优化方法在线演示 [https://www.benfrederickson.com/numerical-optimization/] | * 优化方法在线演示 [https://www.benfrederickson.com/numerical-optimization/] | ||
+ | * 基于神经网络的二分类任务演示 [https://cs.stanford.edu/people/karpathy/convnetjs/demo/classify2d.html] | ||
==开发者资源== | ==开发者资源== | ||
− | |||
− | |||
==高级读者== | ==高级读者== | ||
* 王东,机器学习导论,第一章“绪论”,第十一章“优化方法”[http://mlbook.cslt.org] | * 王东,机器学习导论,第一章“绪论”,第十一章“优化方法”[http://mlbook.cslt.org] | ||
− | * Wolpert, David (1996), "The Lack of A Priori Distinctions between Learning Algorithms", Neural Computation, pp. 1341–1390 [https://web.archive.org/web/20161220125415/http://www.zabaras.com/Courses/BayesianComputing/Papers/lack_of_a_priori_distinctions_wolpert.pdf] | + | * Wolpert, David (1996), "The Lack of A Priori Distinctions between Learning Algorithms", Neural Computation, pp. 1341–1390 [*][https://web.archive.org/web/20161220125415/http://www.zabaras.com/Courses/BayesianComputing/Papers/lack_of_a_priori_distinctions_wolpert.pdf] |
+ | * Sebastian Ruder, An overview of gradient descend algorithms,2017 [https://arxiv.org/pdf/1609.04747.pdf] | ||
+ | * Kirkpatrick, S.; Gelatt Jr, C. D.; Vecchi, M. P. (1983). "Optimization by Simulated Annealing". Science. 220 (4598): 671–680. [https://www.science.org/doi/10.1126/science.220.4598.671] | ||
+ | * Brown et al., Language Models are Few-Shot Learners [https://arxiv.org/pdf/2005.14165.pdf] |
2023年8月8日 (二) 09:48的最后版本
教学资料
扩展阅读
- 维基百科:没有免费的午餐定理 [5]
- 维基百科:梯度下降法[6][7]
- 百度百科:梯度下降法[8][9]
- 知乎:梯度下降法[10]
- 知乎:小批量梯度下降法[11]
- 知乎:动量梯度下降法[12][]
- 维基百科:模拟退火算法 [13][14]
- 百度百科:模拟退火算法[15][16]
- 知乎:模拟退火详解 [17]
- 维基百科:牛顿法 [18][19]
- 维基百科:奥卡姆剃刀[20][21]
- 百度百科:奥卡姆剃刀[22][23]
- 维基百科:过拟合[24][25]
- 维基百科:GPT-3 [26][27]
- 机器之心:当谈论机器学习中的公平公正时,我们该谈论些什么?[28]
- 机器之心:数据增强 [29]
- 知乎:数据增强 [30][31]
- 什么是模型预训练[32]
- 迁移学习 [33]
视频展示
演示链接
开发者资源
高级读者
- 王东,机器学习导论,第一章“绪论”,第十一章“优化方法”[38]
- Wolpert, David (1996), "The Lack of A Priori Distinctions between Learning Algorithms", Neural Computation, pp. 1341–1390 [*][39]
- Sebastian Ruder, An overview of gradient descend algorithms,2017 [40]
- Kirkpatrick, S.; Gelatt Jr, C. D.; Vecchi, M. P. (1983). "Optimization by Simulated Annealing". Science. 220 (4598): 671–680. [41]
- Brown et al., Language Models are Few-Shot Learners [42]