a***m
发帖数: 5037 | 1 by Yann LeCun
Statement from a Slashdot post about the AlphaGo victory: "We know now that
we don't need any big new breakthroughs to get to true AI"
That is completely, utterly, ridiculously wrong.
As I've said in previous statements: most of human and animal learning is
unsupervised learning.
If intelligence was a cake, unsupervised learning would be the cake,
supervised learning would be the icing on the cake, and reinforcement
learning would be the cherry on the cake. We know how to make the icing and
the cherry, but we don't know how to make the cake.
We need to solve the unsupervised learning problem before we can even think
of getting to true AI.
And that's just an obstacle we know about. What about all the ones we don't
know about? |
O**l
发帖数: 12923 | 2 这样搞goog最后一盘一定要赢了
cpu增加10倍 碾压 |
l**********n
发帖数: 8443 | 3 说得没错。主要是广告效应
that
and
【在 a***m 的大作中提到】
: by Yann LeCun
: Statement from a Slashdot post about the AlphaGo victory: "We know now that
: we don't need any big new breakthroughs to get to true AI"
: That is completely, utterly, ridiculously wrong.
: As I've said in previous statements: most of human and animal learning is
: unsupervised learning.
: If intelligence was a cake, unsupervised learning would be the cake,
: supervised learning would be the icing on the cake, and reinforcement
: learning would be the cherry on the cake. We know how to make the icing and
: the cherry, but we don't know how to make the cake.
|
x**w
发帖数: 7947 | 4 lecun说的完全正确啊。 此外dm下一步不是要试从0开始练阿狗吗？只是前景相当难测
。反正跑着看看呗。
无论怎样，目测这版V18是最后一次在公开场合露面。明天告别战。 |
m**c
发帖数: 7349 | 5
that
how to make the icing and
unsupervised learning? 自学成才?
【在 a***m 的大作中提到】
: by Yann LeCun
: Statement from a Slashdot post about the AlphaGo victory: "We know now that
: we don't need any big new breakthroughs to get to true AI"
: That is completely, utterly, ridiculously wrong.
: As I've said in previous statements: most of human and animal learning is
: unsupervised learning.
: If intelligence was a cake, unsupervised learning would be the cake,
: supervised learning would be the icing on the cake, and reinforcement
: learning would be the cherry on the cake. We know how to make the icing and
: the cherry, but we don't know how to make the cake.
|
a***m
发帖数: 5037 | 6 小孩学说话好像真有点无师自通
扔在这个语言环境即可
【在 m**c 的大作中提到】
:
: that
: how to make the icing and
: unsupervised learning? 自学成才?
|
w******8
发帖数: 1078 | 7 这个是阿剌耶识的功能,
【在 a***m 的大作中提到】
: 小孩学说话好像真有点无师自通
: 扔在这个语言环境即可
|
k*l
发帖数: 2574 | 8 和他说话的人都是老师啊。怎么无师自通了？人也是学了很多才能触类旁通的。 |
l*****8
发帖数: 16949 | 9 就是啊。有些东西是unsupervised的，比如见到食物知道怎么吃，只能方面的绝大多数
还是supervised。特别是围棋。也许发明围棋的是unsupervised,但小孩子你不教他他
会知道围棋规则？不能说只有unsupervised learning才是真正的智能把。
【在 k*l 的大作中提到】
: 和他说话的人都是老师啊。怎么无师自通了？人也是学了很多才能触类旁通的。
|
t******l
发帖数: 10908 | 10 无师自通？无师自通那得扔狼群里才算吧。
人群里最傻的语言傻鼻，放猴群里都是百万年一现的天才语言家了。话说津巴布韦的
猴子们正在捶胸顿足，当年万年一遇的神之一手基因突变为啥就错过了。这不都已经
在大森林里捶胸顿足好几百万年了。
【在 a***m 的大作中提到】
: 小孩学说话好像真有点无师自通
: 扔在这个语言环境即可
|
