Quiz for Unsupervised learning Lecture on 03/28
Consider the above plot. How many clusters do you think the data inherently has?
What could potentially go wrong in the above code for k-means ?
Loss might start increasing after some iterations.
Random Initialization might lead to poor clusters.
'@' won't work for dimensions higher than 1000 and would throw an error.
Numpy broadcasting might not happen correctly in some cases.
Which of the following is an INCORRECT statement about Principal Component Analysis (PCA)?
PCA finds the axes along which the variation in the data is highest
PCA uses Singular Value Decomposition
Minimizing PCA Loss is a convex optimization problem
PCA can be used to transform the inputs before applying Supervised Techniques like SVM
Never submit passwords through Google Forms.
This form was created inside of Carnegie Mellon University.
Terms of Service