Lecture 60 — The k Means Algorithm | Stanford University

Thanks for your class...
Well explained!!!

Lucid explanation !!

very useful explanation .

hello
someone can help me to resolve ?
1) Create the core functions:
- polynomial (c, h, x, y)
-Gaussian (standard deviation, x, y)
-sigmoid (alpha, beta, x, y)
-khi-two (x, y)

2) create a function that constructs a gram matrix.

3) Karnelk means classification algorithm

disappointed Stanford - it needed to show the k-means with pictures graphs diagrams - just a dry explanation is no use - hope you will use this feedback - thanks for the attempt

very helpful and easy to understand. Keep up the good work!

good

Let's say I have a high dimensional dataset which contains 100 features. For picking the initial k points if I follow the approach 2 (dispersed) then how can I manually understand the distance as I cannot plot this high dimensional dataset in 2d graph.

Nice Video :-)

best tutorial ever!

Why is there so much saliva?

thank you wonderful video

Excellent start, cleared my initial doubts. Keep it up

unfortunately useless.

Can anyone help me out how to merge cluster if they are close to each other or if they are in a particular direction

I love this video. can you please sent me the link to the next video?

nice explanation. Thank u

what about convergence proof etc ... this is too naive

Excellent explanation. Very concise but covered the right details.

Using another clustering algorithm to pick K points seems to me like a oxymoron.

Nice explanation !!! Thank you

very well done.

awesome !!! great explanation, simply, useful, efficient ! I feel that I really understood the topic... Thank you !

its helpful it you show the calculatins...