R*******N 发帖数: 7494 | 1 是不是可以简单地说,
后者是自动的,前者需要人为设置?
不知道这样理解对不对?
还是说,SL可以有training data,
USL就只是预先设置好的? |
c****r 发帖数: 185 | 2 SL=classification
USL=clustering |
I**********s 发帖数: 441 | 3 In supervised learning, you know the answer and use the answer to direct the
adjustment of parameters to be learned while training.
In unsupervised learning, you don't know the answer. The program learns the
parameters by itself upon the internal relationships of the training data. |
R*******N 发帖数: 7494 | 4 多谢,一般来说,
SVM,HMM,Markov Network,Bayes分别算哪种呢?
the
the
【在 I**********s 的大作中提到】 : In supervised learning, you know the answer and use the answer to direct the : adjustment of parameters to be learned while training. : In unsupervised learning, you don't know the answer. The program learns the : parameters by itself upon the internal relationships of the training data.
|
g*****f 发帖数: 241 | 5 都是SL。
【在 R*******N 的大作中提到】 : 多谢,一般来说, : SVM,HMM,Markov Network,Bayes分别算哪种呢? : : the : the
|
a***n 发帖数: 404 | 6 unsuperised 太难了阿。。。 等于就是高智能发现
【在 g*****f 的大作中提到】 : 都是SL。
|
s******e 发帖数: 285 | 7 supervised: training data has labels,
unsupervised: training data unlabeled.
【在 R*******N 的大作中提到】 : 是不是可以简单地说, : 后者是自动的,前者需要人为设置? : 不知道这样理解对不对? : 还是说,SL可以有training data, : USL就只是预先设置好的?
|
R*******N 发帖数: 7494 | 8 With unlabeled data, how is the training performed?
Solely dependent on its own clustering?
【在 s******e 的大作中提到】 : supervised: training data has labels, : unsupervised: training data unlabeled.
|
o******r 发帖数: 259 | 9 SOM is for USL.
【在 g*****f 的大作中提到】 : 都是SL。
|
I**********s 发帖数: 441 | 10 K-means is another example |