From 70bd2facb3a2cfffdeabd6b86183042f3f8fa90a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Quentin=20GALLOU=C3=89DEC?= <gallouedec.quentin@gmail.com> Date: Thu, 27 Oct 2022 16:37:23 +0200 Subject: [PATCH] Better format --- README.md | 1 - 1 file changed, 1 deletion(-) diff --git a/README.md b/README.md index d217ca7..514c68e 100644 --- a/README.md +++ b/README.md @@ -179,7 +179,6 @@ We also need that the last activation layer of the network to be a softmax layer that perform one gradient descent step using a binary cross-entropy loss. We admit that $`\frac{\partial C}{\partial Z^{(2)}} = A^{(2)} - Y`$, where $`Y`$ is a one-hot vector encoding the label. - The function must return: - `w1`, `b1`, `w2` and `b2` the updated weights and biases of the network, - `loss` the loss, for monitoring purpose. -- GitLab