I am Jay Patel and I am very passionate about Machine Learning and helping you understand the programs behind it in a fun and engaging way.
I can help you learn the algorithms behind successful machine learning models and also building applications and projects. If you like to learn Machine Learning without boring lectures and build awesome applications, then this may be the channel for you.
Machine Learning has its applications everywhere. Image Recognition, Language Translation, Chatbots, speech to text, stock prediction, and many more. It is predicted that 80% of emerging technologies will have an AI foundation.
And we are just starting out in the uses of AI. Now is one of the best times to learn Machine Learning.
Пікірлер
By implementing the same code it is showing an error: weight is not defined what should I do
This is really interesting and simplified. Thank you so much for the handwork you put in
Thnk you very much sir ❤.You helped me a lot.
It is showing can't import sequential from tensorflow. model how to fix this error
while loading the dataset i get an error msg
Love your explanation
At 14:40 why are we multiplying with (1/m), even though it is not mentioned in the formula?
Thank you man please keep doing these kind of videos
Thank you. Will do!
Underrated channel fr
Thanks a lot
Wonderfully explained. Just finished watching all the 12 videos from your playlist.....
Hi Jay "Don't laugh at me, I have always been programing of a external compiler (Java / Matlab) - After launching your github template, the jupyter blank code is not in edit mode, what must I do
Wonderful explanation.
for simplicity how can partial differentiation of L/Z3 be equal to the difference of Z3 , please kindly explain this🙏 @coding lane ??
When creating the bigrams (for each of two adjacent words), the order should matter. But why you insert all the possible combinations in the bigrams list? I think the order of the words as it appear in the corpus is important to capture the relationship between adjacent words.
How the sum over m (number of onsevation) gets included by the matrix multiplication of the matrices that are made of one state's variable. A2,A3, Y etc all are matrices of just one snapshot or just one state of the neural network.
Bro you are great. Respect ++
Thank you so much!
nice explanation. CNN layers do complex jobs of finding edges through filters. So CNN + flatten layer + ANN gives output.
bro can you plese tell, what resources do you follow for learning and such indepth understanding of this concepts?
how to select best features to get the highest possible f1 score
thank you very much
great help. Thanks for all the videos. too good
very nice aaa frr
@codeboosterjp Could you please share your ppt?
Isn't axis=1 row wise summation ?
When finding del(Cost)/del(Bias), is it really column wise summation instead of row wise summation because we are reducing rectangular matrix of n3*m to n3*1 vector? I might be wrong, but I think there is a mistake
can you please reference the values of beta1 and beta2 and epsilon ?
The best ever explanation with detailed mathematical explanation
why 2m specifically? There are differences of 2m points, but there are only m values.
Hi @Coding Lane, I dont get the part at 7:05 dL/df. Can you explain where did f2'(Z2) go?
You made a small mistake while typing the code for derivative_tanh(x) function. ✔ The correct code will be : def derivative_tanh(x): return 1 - np.power(np.tanh(x), 2)
thanks i really enjoy the playlist
At 8:00, Is there a mistake? You should take partial derivative with respect to a?
how does relu solve the vanishing gradient problem since some part of the gradient is zero for x < 0?
Maybe best explanation on YT on this topic, i am looking at hours of content and this 18 min video helped me a ton, Thank you!
cost function for binary classification that you mentioned is also called as entropy. am I right?
i still dont understand one thing what does B mean here is it the direction or bias
well explanation brother. keep it up
i had a doubt you mentioned gray scale goes from 0 to 255 so the filter you say has negative values too how is that possible
Thanks
Does relu makes the f(x)=0 even if the x is very small but >0? because tanh/sigmoid the rate of change of gradient becomes very small but still >0, whereas in the relu the f(x) seems to be 0 only when x<=0
when you summarized the formula @9:00 min, wont there be an 1/m upfront? as that's what you explained at the top handwritten
i am only getting 50% accuracy
Really informative. Thankyou
This is so well explained.. thankyou
cost function can be any function for those who are asking why dividing by 2 . of course the ones that makes sense and we can minimize is a function power of 2 so that's why
Thank you for your dedication and about the quizzes, I can't find it.
nice bro . i couldn't understand what prof andrew was tryna say but you did a great job , thnks man
explanation of the concept was so good! the concept became easy to understand! Thanks for this video!
thank you
You are a good teacher. Congratulations ❤