Video
Unknown · 0:00
In fast.ai Part 2, Lesson 13, Jeremy Howard builds a two-layer MLP for MNIST and works out its backpropagation by hand. Backprop turns out to be the chain rule applied layer by layer, plus storing intermediate values...
Unknown · 0:00
In fast.ai Part 2, Lesson 13, Jeremy Howard builds a two-layer MLP for MNIST and works out its backpropagation by hand. Backprop turns out to be the chain rule applied layer by layer, plus storing intermediate values...
Redirecting...