Probability Density Functions - EXPLAINED!

[@harshkumaragarwal8326]

At 24:36, derivative of of a positive function need not to be positive. Am I missing something

[@CodeEmporium]

Yea you’re right. What I should have said was “the cumulative density function is a monotonically increasing function. Because it always increases, the derivative at every point will be non negative.” Thanks for the catch :)

[@harshkumaragarwal8326]

@@CodeEmporium Thanks for the videos, helps me a lot :)

[@MateoDH2403]

thanks man, loving how your channel have it all, from the basics to advanced knowledge, really really useful!

[@mustafizurrahman5699]

❤love you man. Extraordinary video for the intuition

[@gloriasegurini3957]

Hello CodeEmporium. Thanks a lot for this really enlightens video. Let me ask you something: can we interpret the value on the y axis of the pdf graphic for a specific point x as the likelihood? I always struggle on this detail

[@therasmataz2168]

It is indeed likelihood. it indicates the likelihood of a specific value occurring within a certain range of the x-axis variable.

[@akramsystems]

This answers the what is it question, but not why it’s important or how to generate the probability mass distribution.

[@CodeEmporium]

Yea. This is video 5 of a 6 part series on Probability for Machine Learning. I will explain how all concepts tie together in my next weeks video. But if you are curious for a peak, you can check the medium blog post in the description for the “why is this useful in machine learning “

[@akramsystems]

Yes I’ll definitely check it out ! Thanks for the video none the less!

[@CodeEmporium]

Of course! Thanks for watching :)

[@ishworpoudel2399]

What we can expect from your vedio what we can learn from you what’s your youtube channel about data science or statistics

[@therasmataz2168]

@15:38 Your explanation felt a little contrived or forced. The probability density function is just the probability of the random variable per unit of the random variable hence the analogy with density as mass per unit volume in physics. It's the probability per unit of the random variable so its units for this example would be per cm (cm^-1).