Dude, i for the longest time felt like my understanding of moving averages and RmsProp was missing something and i found it in this video. You have no idea how grateful i am to your channel. Thank you, teachers tend to jump over important concepts without explaining them 🎉
Your explanations are as always clear and very useful. One of the best on UA-cam, and again I say it as a teacher myself (not in the AI field). Yet, an issue is being miss-explained in literally all available explanations on UA-cam. For some reason, you are also among them. The issue is that you forget to mention that the loss surface is unique and different for EVERY observation and might potentially have minimums in different places for different observations. This is extremely important to understand especially in the context of stochastic gradient descent
@@CodingLane Hope I not insulted you, If i did, my appologies. Just trying to sullply you constructive feedvacks As being said I think you are one of the best on you yube
A small doubt, in the RMSprop as W and B both are affected by the SEWMA then the B direction is also affected by db, thus the steps in the B direction will also get checked, so won't it too decrease the learning rate and defy our whole purpose?
Dude, i for the longest time felt like my understanding of moving averages and RmsProp was missing something and i found it in this video. You have no idea how grateful i am to your channel. Thank you, teachers tend to jump over important concepts without explaining them 🎉
Hehe… thank you so much for expressing this 😇
Explained it best. After many years finally got it
😇😇
a life saver! thank you soo much for sharing this with us
You’re welcome!
Your explanations are as always clear and very useful. One of the best on UA-cam, and again I say it as a teacher myself (not in the AI field).
Yet, an issue is being miss-explained in literally all available explanations on UA-cam.
For some reason, you are also among them.
The issue is that you forget to mention that the loss surface is unique and different for EVERY observation and might potentially have minimums in different places for different observations. This is extremely important to understand especially in the context of stochastic gradient descent
Hi, thanks for the suggestion. Yes, its true
@@CodingLane Hope I not insulted you, If i did, my appologies. Just trying to sullply you constructive feedvacks
As being said I think you are one of the best on you yube
You explained it very smooth and clear, thank you!
Thank you! Happy to help!
This is the best explanation so far. Thanks for the great work
Thank you so much! Glad it helped! 🙂
Best explanation out there. Thanks a lot!
Thanks a lot for this!
Thank you very much for the awesome explanation.
You made it super easy. Thanks for sharing
You’re welcome 😇
A small doubt, in the RMSprop as W and B both are affected by the SEWMA then the B direction is also affected by db, thus the steps in the B direction will also get checked, so won't it too decrease the learning rate and defy our whole purpose?
i still dont understand one thing what does B mean here is it the direction or bias
Very nice explanation..Keep up the good work
Thank you so much. I appreciate it!
Nice Explanation, Keep it up.
Thank you!
Amazing!
thank you
good