Backpropagation: How Neural Networks Learn

[@markr9640]

Nicely done. Love the coloured up maths symbols. Realy makes it look more cuddly and easy.

[@apianoadventure]

7:50 'say we have a neuron i connected to every neuron k in the following layer': proceeds to calculate dL/dyi ??? How does the output yi depend on the next weights ???
A few minutes before with the first example, you calculated dL/dyj ?

[@saminsolouki]

what is xj hat ? why "xj hat = yj + wij"?

[@alicefox538]

notation could be clearer

[@pensiveintrovert4318]

You need to be more monotone, to help viewers to feel more excited about backprop.

[@learning_with_irving4266]

What's wrong with backdrop?