Machine Learning (Stanford) Coursera Neural Networks: Representation Quiz (Week 4, Quiz 1) for the github repo: https://github.com/mGalarnyk/datasciencecoursera/tree/master/Stanford_Machine_Learning

Neural NetworksRepresentationStanfordCoursera.md

Machine Learning Week 4 Quiz 1 (Neural Networks: Representation) Stanford Coursera

Github repo for the Course: Stanford Machine Learning (Coursera)
Quiz Needs to be viewed here at the repo (because the image solutions cant be viewed as part of a gist)

Question 1

True or False	Statement	Explanation
False	A two layer (one input layer, one output layer; no hidden layer) neural network can represent the XOR function.	We must compose multiple logical operations by using a hidden layer to represent the XOR function.
True	Any logical function over binary-valued (0 or 1) inputs x1 and x2 can be (approximately) represented using some neural network.	Since we can build the basic AND, OR, and NOT functions with a two layer network, we can (approximately) represent any logical function by composing these basic functions over multiple layers.
False	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 output unit, 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.	The outputs of a neural network are not probabilities, so their sum need not be 1.
True	The activation values of the hidden units in a neural network, with the sigmoid activation function applied at every layer, are always in the range (0, 1).	None Needed

Question 2

Answer	Explanation
AND

Question 3

Answer	Explanation
	This correctly uses the first row of Θ(2) and includes the "+1" term of a(2)0

Question 4

Answer	Explanation
a2 = sigmoid (Theta1 * x);	In the lecture's notation a(2) = g(Θ(1)x), so this version computes it directly, as the sigmoid function will act element-wise.

Question 5

Answer	Explanation
It will stay the same.	Swapping Θ(1) swaps the hidden layers output a^{(2)}. But the swap of Θ(2) cancels out the change, so the output will remain unchanged.

2: NAND...option 1 is coorect
3:a(1)(1) option with all one prefix on a..option 1