Great lecture. Props to your cameraman for following you.
@aze905 жыл бұрын
Great teacher!
@kathirs17 жыл бұрын
Awesome explanation sir.. Make more videos please
@gautamkarmakar34437 жыл бұрын
Awesome lectures!! Is there anyhow I can get the slides?
@rauldearaujo71887 жыл бұрын
Great explanation! Thank you! :D
@adels13884 жыл бұрын
I think Vw is a column of W' not a row of it. am I right?
@mubintirsaiwala71414 жыл бұрын
Yes, you're right.
@gregarityNow4 жыл бұрын
seconded
@EzraSchroeder3 жыл бұрын
@26:16 why can we not guarantee that the output vector is sparse at test time?
@leeris192 ай бұрын
Actually, I think we can guarantee it if we train the network enough but that is actually a bad outcome as it suggests overfitting. Ideally, we want the outcome to be not that sparse in order for the model to generalize better. The model should have this notion that "I know this is what should happen, but it's still possible that other results may happen".
@gregarityNow4 жыл бұрын
at 44:57 you clandestinely added a minus. I think that should not be there if you are maximizing!