注册一亩三分地论坛,查看更多干货!
您需要 登录 才可以下载或查看附件。没有帐号?注册账号 
x
本帖最后由 fyswords 于 2017-8-11 09:28 编辑
Which of the following statementsare true? Check all that apply.
A. A two layer (one input layer, one output layer; no hidden layer) neural networkcan represent the XOR function.
异或两层不够,需要三层,不选?
B. The activation values of the hidden units in a neural network, with the sigmoidactivation function applied at every layer, are always in the range (0, 1).
应该选?
C. Suppose you have a multi-class classification problem with three classes, trained with a 3 layer network. Let a(3)1=(hΘ(x))1 be the activation of the first outputunit, and similarly a(3)2=(hΘ(x))2 and a(3)3=(hΘ(x))3. Then for any input x, it must be the case that a(3)1+a(3)2+a(3)3=1.
不是很理解classification的明确定义,如果各个分类是排他的,有明确界限的,就应该只有一个是1剩下都是0吧,加起来是1.应该选上?
D. Any logical function over binary-valued (0 or 1) inputs x1 and x2 can be (approximately)represented using some neural network.
应该是对的吧,逻辑表达式都可以用逻辑门搭出来,所以也都可以用神经网络?
这道题尝试了3次还没选对,求教
又做了一下,应该选BD。现在的问题就是请教C选项了
|