评论
打印
There's an old joke, statisticians like to tell which is that your vocabulary size is correlated with your hand size. And it's actually true.
有个古老的笑话，统计学家喜欢讲，一个人的词汇量与手掌的大小相关。这是真的。
If you go across the whole population, measure everybody's hand size and everybody's vocabulary, then people with bigger hands on average have bigger vocabulary.
如果你统计所有人，测量每个人的手的大小和每个人的词汇量，那么平均而言，双手更大的人，词汇量就更大。
But does that mean that having a bigger hand gives you a bigger vocabulary, as opposed to studying and reading books, which might?
但是，这是否意味着手更大就会拥有更大的词汇量，而不必通过学习或阅读？
Well, no. It just means that adults tend to know more words than kids, and they tend to have bigger hands.
答案是否定的。这只是意味着成年人比孩子懂更多的词汇，而且他们的手也更大。
That something is causing them to learn words and causing them to grow their hands, they're not really quite the same thing.
似乎有某种原因让他们学习单词并导致他们的手长大，但其中的原因不同。
So causation, it would be if growing your hand actually made you grow your vocabulary. But that's not there. We just have a correlation.
因此，似乎是手长得更大会让词汇量更大。但不存在这种事。这里只有一个相关性。
Deep learning is kind of fancier than correlation. But to a first approximation that's what it's doing. It is correlation. It doesn't have ways of representing causal relationships.
深度学习比相关性更复杂。但大致看来，是这回事，存在相关性，但无法表明因果关系。
So if we wanted to ask a deep learning system, does growing bigger hands mean you have a bigger vocabulary?
因此，如果我们想问一个深度学习系统，越大的手是否意味着拥有更大的词汇量？
The deep learning system can say, well, I have a number of observations here. They certainly seem to be correlated.
深度学习系统可以会说，嗯，我在这里有一些研究。他们似乎是相关的。
But it can't say that what causes your hand to grow is all kinds of metabolic processes, and what causes your vocabulary to increase is all kinds of learning experiences.
但是，不能说导致手长大的原因是各种代谢过程，而导致词汇增长的原因是各种学习经历。
And so it has no way to even really get into the question of whether there's a causal relationship between your hand size and your vocabulary.
因此，它甚至无法真正解决手的大小和词汇量之间是否存在因果关系的问题。
It can just note that they're correlated. And that could be fine for some purposes.
深度学习系统只会认为，两者是相关的。在一些方面，这种结果可能无所谓。
If you wanted to pick out the people in the population with the biggest vocabulary, maybe it will help.
如果你想从人群中挑选出词汇量最大的人，这也许会有所帮助。
If you wanted to know what the mechanisms are, why these things are correlated,
如果你想知道其中的机制是什么，为什么这些东西相关，
and whether one is causing the other-which you'd probably want to know-then deep learning is not your tool for that.
以及是否是一种情况导致了另一种情况（你可能想知道），那么深度学习并不是解决这些的工具。
