Probably Approximately Correct (PAC)Learning ( KTU CS467 Machine Learning Module 2)

[@akshayanilkawale5970]

There is big difference in reading and teaching

[@sergiotorrijos5911]

After some time I think I've understood it thanks to this video. Very clear explanation!!

[@nishantkamboj6543]

Never saw a great explanation than this ❤️

[@kurmangee58]

Beautifully explained. Thank you!

[@mottymathews5832]

Great explanation. Thank you

[@ercanatam6344]

There are some notational confusions: at 4:32, you use Error (h), then write this P(CXORh) and then use "Pr". What is difference between Error (h) and P(CXORh)? For probability you use both "P" and "Pr", that is not consistent.

[@tianshizhang458]

Detailed explanation and good PPT. I like it!

[@haji3787]

Great explanation. Thanks!

[@yahyaemara6617]

Great video!, Thanks for explanation

[@kalpanan343]

Very nice

[@abdokabany4807]

Thank you very much that was really helpful

[@saketnarendra8864]

Thank You maam, really well explained

[@aldenmenzalgy3313]

Amazing!!!

[@nitya6828]

Can I get ppt of this video?

[@harsh4749]

14:40 where does inequality eq came from

[@sanITtips]

By applying Hoeffinding Inequality

[@ramapathivada]

Asalu aaa error values ela vesaru?epsilon =0.05 endhuku

[@ALEXPJOSEPHBTechCSEA-]

thanks

[@akhilkumar220k.s9]

Ma'am could please share us the notes if possible.

[@fatimaishtiaq8422]

thank you. but can u give me its coding?

[@vishaltanawade7637]

We can read ,,,,

[@9860215497]

Why epsilon and delta is upper bounded by 1/2?

[@rajkane989]

1/2 is just a conveniently small value that can be made arbitrarily small. Having error over 50% or probability less than 50% would make for a useless model