随便说几句关于机器学习和物理
1 Comment
Post a comment
细推物理须行乐 何用浮名绊此身
今天看到的一个关于机器学习的想法挺有意思。也许人类最终会发现 几千年积累下来的认识世界的方式 都只是受人脑有限的计算力而发展出的局部最优解。包括现在我们理解的物理定律。什么是物理？物理学家普遍有种倾向就是认为物理定律必当是简洁的。有句名言是给我四个参数我能画一头大象，给我五个参数我能让大象的鼻子动。但倘若某一天 机器学习用几亿个参数暴力做物理预测 比人类用理解的方式做出来的都要更好呢？说实话现代的物理也其实一点都不简洁了 看似简洁的背后都有一大堆冗长的数学符号的定义藏着呢。期待哪天机器学习可以各种预测 Navier-Stokes 湍流的性质。
physixfan
eaglefantasy
Eagle_Fantasy
宇宙的心弦
Traction Theme by The Theme Foundry
Copyright © 2024 physixfan. All rights reserved. 
宇宙的心弦 by physixfan is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.
局部最优解都未必，自然演化从来都是现挑选就现用，只能证明一阶导数往局部最优解的方向去。另外，如何规定损失函数也是个问题