But what does a trained Convolution Neural Network actually learn? VISUALIZED!

[@aneeshsathe4850]

great video! keep 'em coming 👌🏼

[@TP-ct7qm]

Awesome video! Among the best explanations of CNNs and Convolution I've seen on YT.

[@farrugiamarc0]

One of the best convolution explanations I have seen so far. Well done!

[@weixie4943]

Thank you! As the others have commented, a great explanation, as always! At 4:44, should the purple bars be flipped about the "x-axis" from what is shown, since at the left edges of the contiguous red "stretches"/"blocks", the only part of the kernel that overlaps is the negative/"down" bar, and vice-versa at the right edges? Thanks again!

[@avb_fj]

Great point! You are correct. Basically, the general "signal processing" formula for convolution flips the kernel along the X-axis within it (something like _sum{f(t) g(T - t)} where f(.) = signal and g(.) = kernel). But most of the video explains convolution (how it is used in deep learning) as "correlation" (basically _sum{f(t) g(t)} ) where the flipping is not assumed. At 2:16 I mentioned the manual flipping step, but for the example at 4:44, I skipped it. Thanks for pointing that out!

[@Triviani7]

Amazing explanation. The inner workings of CNNs weren’t really clicking for me until now.

[@avb_fj]

Thanks! Glad it was helpful!

[@PriyanshuKumar-ss3qv]

Great video

[@mbpiku]

Great video.