"supervise verse unsupervised,, all this means is that supervised problems typically have a training dataset where you have a set of features and you have an output. You use the output to train and get new data that may or may not have labels that are associated with it" .... thank you sir
This would have been a lot more interesting had we seen the general algorithms, code, data, and output. This was a lot of opinion, but very little proven fact.
"supervise verse unsupervised,, all this means is that supervised problems typically have a training dataset where you have a set of features and you have an output. You use the output to train and get new data that may or may not have labels that are associated with it" .... thank you sir
Love how you say "the infamous cheat-sheet' ^^
An excellent brief overview of ML for beginners in that field, which I am. I'll be starting Ng's class through Coursera soon.
Awesome! Very clear.
good work!
very clear
I watched the presentation and the questions but failed to find the "discussion of relevance vector machines"
Slides and code: github.com/kastnerkyle/SciPy2013
This would have been a lot more interesting had we seen the general algorithms, code, data, and output. This was a lot of opinion, but very little proven fact.
After all,it is just a 'Gentle Intro' to adopt as a guideline.You can check the references (scikit documentation and coursera ML course).Regards
cats
Thanks! 3000 bits via *****