best explanation so far! thank you. i have tried it in R using the neuralnet function with your dataset. even though i get the same coefficients with the log regression the weights and bias using the ANN are not the same. they are much lower. any idea why? =/
True, you can use just one output node when you predict just two categories. The R code I provided generates two output nodes but if you try TensorFlow in Python, it will use just one output if you set loss='binary_crossentropy'.
the best i have seen so far
Just magistral 👏👏
You are Brilliant. i could not understand the whole concept until you explained in this video.
Perfect!
Omg, I have tried to understand ANN without success until now. Thank you!
u r a wondeful tutor. God bless u
The notation on the left-hand side of the equations at 20:00 and 20:45 should be f(x) and not f(z).
Thank you, looking forward to your next video about ANN
Thank you!
Wow... Great expectation as always 👍
best explanation so far! thank you. i have tried it in R using the neuralnet function with your dataset. even though i get the same coefficients with the log regression the weights and bias using the ANN are not the same. they are much lower. any idea why? =/
Did you use the exact same code as shown at 24:52?
jeeez. i have, but missed the threshold. that was it! many thanks!!!
can you please provide R code for finding values of b0 and b1
It is provided at 24:51 in the video.
How are the 2.747 and 5.7 derived?
That is explained at 11:30 and forward.
why using 2 output nodes? isn't P(healthy) equal to 1-P(cancer)?
True, you can use just one output node when you predict just two categories. The R code I provided generates two output nodes but if you try TensorFlow in Python, it will use just one output if you set loss='binary_crossentropy'.
@@tilestats
Thanks for the clarification
for the first calculation, why u get -0.251?, i get -0.26
I think it is just due to rounding from previous steps.