确实是绝世好贴, 聊天灌水区应该多一点这种类型的帖子。
收藏的一段话(出处忘了):
Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an “intelligence explosion,” and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make, provided that the machine is docile enough to tell us how to keep it under control.
不不,我是在medium上一篇普通的闲扯AI的文章里看到的这段话/这个概念
元学习就是让机器学会该如何学习的,最近比较火,具体的我也不太清楚,感兴趣的话可以看下这篇博客:
From zero to research — An introduction to Meta-learning
额,给出的是emacs-lisp代码,如果需要直接在GIMP里执行的话:
(let ((pi (* 4 (atan 1))))
(let ((round-table-area
(* pi (expt (- 1900 100)
2)))
(square-table-area
(* (- 500 100)
(- 605 5)))
(baozi-area
(* pi (expt (- 2000 1900)
2))))
(truncate
(/ (+ round-table-area square-table-area)
baozi-area))))
可以了,赞!!!
……
对自动化效率的思考和争论永不停止啊
好像是 I. J. Good? , 英国超帅数学家, fast Fourier transform 先行者(向他致敬!)。
有印象是在 2001: A Space Odyssey 中的那个 HAL 9000 ?
什么黑科技?gimp支持lisp语法?
Gimp的开发人员真是geek啊
reinforcement learning, self learning有很多这方面的研究的
似曾相识,忘了在哪看到过类似的问题。
这个确实很方便,但是如果想要训练新的 object detection model 就得自己动手从更基础的做起了:
OlafenwaMoses commented on Jun 22, 2018
In future versions of ImageAI, we will support training object detection models on new and custom images.
恩,前段时间在resnet基础上训练了个能看懂包子的模型。但我对imageAI也不是很熟,不太清楚怎么让它调用新的模型来做object detection,应该是有办法的吧,虽然按你引用的那话,貌似官方没给出接口 。最近很忙,也没来的及hack imageAI。
为啥没人用opencv模板匹配:joy:
真人工智能
以前有卖活体葫芦娃的,这道题也可以用“活体人工智能”来解决:sob: