Q1- Consider a simple neural network with k hidden layer. Further assume that input layer and all hidden layers contain n neurons each, and output layer has a single neuron. Prove that if none of the neurons contain
any nonlinear activation function (e.g. sigmoid etc.) then this neural network can actually be represented without any hidden layers at all. You may assume that n = k = 3 for your proof.
Ans- Output of neural network is given by
where is the input vector and
are weight matrix of edges from
layer to
layer. Note that
is just a row vector. Let
be the matrix product
. Clearly, a neural network without any hidden layers with weight vector equal to
, is equivalent to our network.
Q2- Prove Jensen’s inequality, i.e.,
E [ζ(X)] ≥ ζ(E [X])
for a convex function ζ and a random variable X.
Ans-
Consider a line that is tangent to the graph of ζ function at the point E(X) – let be the equation of this line. Note that all points of ζ function are above or equal to all points on
. Then,
![](https://itu18.wordpress.com/wp-content/uploads/2020/01/image.png?w=634)
where 1 holds because all points of ζ are on or above and 2 holds because of linearity of expectation.
Q3- Prove that for an invertible symmetric matrix A with real eigenvalues the eigenvalues of
are given by the set:
{}
Assume that these eigenvalues are for the unit norm eigenvectors.
Ans- We know that for any arbitrary eigenvector
multiplying by the inverse whose existence guaranteed,
Thus,
Therefore, reciprocals of all eigenvalues of are eigenvalues of
and vice versa. It is easy to see that there can not be anymore eigenvalues.
Q4- Derive Moment Generating Function of a Poisson random variable.
Ans- Let X be poisson, then
Which is,
We have,
Q5-
Let A, B, C be three cabinets containing two coins each. The cabinet A containing 2 gold coins, B containing 2 silver coins, and C contains a silver coin and a gold coin. You open one of the cabinets uniformly at random, and pick one of the coins. If you picked a gold coin then what is the probability that the other coin in that cabinet is gold also.
Ans- Let be the event that
coin is gold coin then, we need to find P(G2|G1), we have
![](https://itu18.wordpress.com/wp-content/uploads/2020/01/image-1.png?w=217)
We know that (G1 ∩ G2) is the event that we pick cabinet A, and P(G1) is 1/2. Therefore,
![](https://itu18.wordpress.com/wp-content/uploads/2020/01/image-2.png?w=200)
If we pick a gold coin, the sample space automatically becomes 2 instead of 3 (as one cabinet has only silver coins). As it is uniform both event A and event B would have probability 1/2. Is that not correct too?
LikeLiked by 1 person