Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Backprop/source.txt
Original file line number Diff line number Diff line change
Expand Up @@ -100,7 +100,7 @@ $$ a_k^l = \sigma(z_k^l) $$

Now finally calculate the input sum of a neuron $m$ in layer $l+1$.

$$ z_m^{l+1} = \sum_{k} w_{mk}^{l+1} a^l_k + b_m^l $$
$$ z_m^{l+1} = \sum_{k} w_{mk}^{l+1} a^l_k + b_m^{l+1} $$

Here we have gone forward one step in the layers, from the activations in layer $l-1$ to the input sums of neurons in layer $l+1$. An error function C is defined using one example from our training data, and its derivative is calculated with respect to a single weight in layer $l$.

Expand Down