http://cslt.org/mediawiki/index.php?action=history&feed=atom&title=%E7%AC%AC%E5%8D%81%E4%B8%89%E7%AB%A0_%E5%AD%A6%E4%B9%A0%E7%AD%96%E7%95%A5 2026-04-04T09:06:50Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://cslt.org/mediawiki/index.php?title=%E7%AC%AC%E5%8D%81%E4%B8%89%E7%AB%A0_%E5%AD%A6%E4%B9%A0%E7%AD%96%E7%95%A5&diff=38819&oldid=prev 2022-08-03T03:03:17Z

<p>以“==教学资料== *<a href="/mediawiki/index.php/%E6%95%99%E5%AD%A6%E5%8F%82%E8%80%83-13" title="教学参考-13">教学参考</a> *[http://aigraph.cslt.org/courses/12/course-13.pptx 课件] *小清爱提问：什么是爬山法？[https://mp.we...”为内容创建页面</p> <p><b>新页面</b></p><div>==教学资料==<br /> *[[教学参考-13|教学参考]]<br /> *[http://aigraph.cslt.org/courses/12/course-13.pptx 课件]<br /> *小清爱提问：什么是爬山法？[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&amp;mid=2247486886&amp;idx=1&amp;sn=a9959dfb953fd7383589236676d6bb08&amp;chksm=c3080764f47f8e72809d3502ecdd0da6940d680fc9ecb0423f7aeec504bcb83026cdb544a11a&amp;scene=178#rd]<br /> <br /> <br /> <br /> ==扩展阅读==<br /> <br /> * 维基百科：没有免费的午餐定理 [http://aigraph.cslt.org/courses/12/No_free_lunch_theorem.pdf]<br /> * 维基百科：梯度下降法[http://aigraph.cslt.org/courses/12/梯度下降法.pdf][http://aigraph.cslt.org/courses/12/Gradient_descent.pdf]<br /> * 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]<br /> * 知乎：梯度下降法[https://zhuanlan.zhihu.com/p/36902908]<br /> * 知乎：小批量梯度下降法[https://zhuanlan.zhihu.com/p/72929546]<br /> * 知乎：动量梯度下降法[https://www.jiqizhixin.com/graph/technologies/d6ee5e5b-43ff-4c41-87ff-f34c234d0e32][]<br /> * 维基百科：模拟退火算法 [http://aigraph.cslt.org/courses/12/模拟退.pdf火][http://aigraph.cslt.org/courses/12/Simulated_annealing.pdf]<br /> * 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]<br /> * 知乎：模拟退火详解 [https://zhuanlan.zhihu.com/p/266874840]<br /> * 维基百科：牛顿法 [http://aigraph.cslt.org/courses/12/Newton's_method.pdf][http://aigraph.cslt.org/courses/12/牛顿法.pdf]<br /> * 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]<br /> * 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]<br /> * 维基百科：过拟合[http://aigraph.cslt.org/courses/12/Overfitting.pdf][http://aigraph.cslt.org/courses/12/過適.pdf]<br /> * 维基百科：GPT-3 [http://aigraph.cslt.org/courses/12/GPT-3-zh.pdf][http://aigraph.cslt.org/courses/12GPT-3-zh.pdf/]<br /> * 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]<br /> * 机器之心：数据增强 [https://www.jiqizhixin.com/articles/2019-12-04-10]<br /> * 知乎：数据增强 [https://zhuanlan.zhihu.com/p/38345420][https://zhuanlan.zhihu.com/p/41679153]<br /> * 什么是模型预训练[https://paddlepedia.readthedocs.io/en/latest/tutorials/pretrain_model/pretrain_model_description.html]<br /> * 迁移学习 [https://baike.baidu.com/item/%E8%BF%81%E7%A7%BB%E5%AD%A6%E4%B9%A0/22768151]<br /> <br /> <br /> ==演示链接==<br /> <br /> <br /> * 优化方法在线演示 [https://www.benfrederickson.com/numerical-optimization/]<br /> * 基于神经网络的二分类任务演示 [https://cs.stanford.edu/people/karpathy/convnetjs/demo/classify2d.html]<br /> <br /> ==开发者资源==<br /> <br /> ==高级读者==<br /> <br /> * 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]<br /> * Wolpert, David (1996), &quot;The Lack of A Priori Distinctions between Learning Algorithms&quot;, 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]<br /> * Sebastian Ruder, An overview of gradient descend algorithms,2017 [https://arxiv.org/pdf/1609.04747.pdf]<br /> * Kirkpatrick, S.; Gelatt Jr, C. D.; Vecchi, M. P. (1983). &quot;Optimization by Simulated Annealing&quot;. Science. 220 (4598): 671–680. [https://sci2s.ugr.es/sites/default/files/files/Teaching/GraduatesCourses/Metaheuristicas/Bibliography/1983-Science-Kirkpatrick-sim_anneal.pdf]<br /> * Brown et al., Language Models are Few-Shot Learners [https://arxiv.org/pdf/2005.14165.pdf]</div>

Cslt