Neural Network RMSE and Log Loss Error Calculation from Scratch (4.5)

[@anuvratanand5610]

Hey I’m a student from India You’re an amazing person for putting this on KZbin and an even better teacher Thanks a ton

[@BiancaAguglia]

A great video, Jeff. Going through these calculations by hand is super useful. It's another step in truly understanding ML models and, consequently, becoming an expert at data science and ML. 😊

[@davidrfarris]

What white board software do you use for you lessions? I am thinking of doing a KZbin on database design and setup.

[@HeatonResearch]

For that one I just used an iPad with an Apple pencil and recorded from a laptop.

[@davidrfarris]

@@HeatonResearch thank you

[@pardeepsangruri]

hi Jeff, i have a problem understanding the example in the sklearn documentation from sklearn.metrics import log_loss >>> log_loss(["spam", "ham", "ham", "spam"], ... [[.1, .9], [.9, .1], [.8, .2], [.35, .65]]) 0.21616... can you please explain this and extend the log_loss idea to multiclass classification. Where they take np.argmax of true_values and subtract the predicted. can you please make a video and expain this concept. Thanks a lot for making this great video

[@anandtewari8014]

how do you pass class Label as input in the machine in classification problems?

[@HeatonResearch]

If they are input, they need to be encoded to dummy/one-hot values.

[@subhashpujari]

Hi Jeff, Thank you very much for such a nice explanation. How one can extend it for a multiclass problem?

[@ronmedina429]

I found that writing things by hand has helped me understand the algorithms more. Thanks, Mr. Heaton. Also I now know that you don't have to have good handwriting to become successful in academia. ;-)

[@HeatonResearch]

Good handwriting can actually hold you back! :-) Bad handwriting actually caused one of my teachers in grade school to suggest to my parents that they should buy a computer type reports.

[@konstantinkanchev889]

great vid