Artificial neural networks (ANN) - explained super simple

www.tilestats.com/
1. What is a neural network?
2. How to train the network with simple example data (1:10)
3. ANN vs Logistic regression (06:42)
4. How to evaluate the network (07:14)
5. How to use the network for prediction (09:23)
6. How to estimate the weights (10:25)
7. Understanding the hidden layers (16:30)
8. ANN vs regression (20:56)
9. How to set up and train an ANN in R (23:08)

[@meshackamimo1945]

u r a wondeful tutor. God bless u

[@yolavictoria472]

Thank you, looking forward to your next video about ANN

[@tedransom8087]

Omg, I have tried to understand ANN without success until now. Thank you!

[@firstkaransingh]

Wow... Great expectation as always 👍

[@Salvador_Dali]

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? =/

[@tilestats]

Did you use the exact same code as shown at 24:52?

[@Salvador_Dali]

jeeez. i have, but missed the threshold. that was it! many thanks!!!

[@learning_with_irving4266]

How are the 2.747 and 5.7 derived?

[@tilestats]

That is explained at 11:30 and forward.

[@a.mo7a]

why using 2 output nodes? isn't P(healthy) equal to 1-P(cancer)?

[@tilestats]

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'.

[@a.mo7a]

@@tilestats
Thanks for the clarification