subject

4. Question 4

Suppose you have a dataset with m = 1000000m=1000000 examples and n = 200000n=200000 features for each example. You want to use multivariate linear regression to fit the parameters \thetaθ to our data. Should you prefer gradient descent or the normal equation?

A. The normal equation, since gradient descent might be unable to find the optimal \thetaθ.

B. Gradient descent, since it will always converge to the optimal \thetaθ.

C. The normal equation, since it provides an efficient way to directly find the solution.

D. Gradient descent, since (X^TX)^{-1}(XTX)-1 will be very slow to compute in the normal equation.

ansver
Answers: 2

Another question on Computers and Technology

question
Computers and Technology, 22.06.2019 10:50
A911 dispatcher is the sole sender of messages to all police officers. while on patrol, officers communicate with the dispatcher who, in turn, relays messages to other officers. the officers do not communicate directly with one another. this illustrates a network.
Answers: 1
question
Computers and Technology, 23.06.2019 18:30
This program should be a short piece of code that prints all of the positive integers from 1 to 100 as described more fully below. the program may contain multiple methods, and if using an oo language, should be contained within a single class or object. the program should be designed so that it begins execution when invoked through whichever mechanism is most common for the implementation language. â–ş print out all positive integers from 1 to 100, inclusive and in order. â–ş print messages to standard output, matching the sample output below. â–ş in the output, state whether the each integer is 'odd' or 'even' in the output. â–ş if the number is divisible by three, instead of stating that the number is odd or even, state that the number is 'divisible by three'. â–ş if the number is divisible by both two and three, instead of saying that the number is odd, even or divisible by three; state that the number is 'divisible by two and three'. â–ş design the logic of the loop to be as efficient as possible, using the minimal number of operations to perform the required logic. sample output the number '1' is odd. the number '2' is even. the number '3' is divisible by three. the number '6' is divisible by two and three.
Answers: 1
question
Computers and Technology, 23.06.2019 20:00
What multimedia system creates an immersive, real-life experience that the user can interact with?
Answers: 1
question
Computers and Technology, 23.06.2019 21:20
For positive constants a and b, the force between two atoms in a molecule is given f(r) = −a r2 + b r3 , where r > 0 is the distance between the atoms. note: a and b are upper case letters. (a) find f '(r) = (b) find the critical point for f(r). r = (c) find f ''(r) = (d) find the value of r so that f ''(r) = 0.
Answers: 1
You know the right answer?
4. Question 4

Suppose you have a dataset with m = 1000000m=1000000 examples and n = 200...
Questions
Questions on the website: 13722360