From 461a27df812418351412483e49a1a5f6f35e9b54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=9D=D0=B8=D0=BA=D0=BE=D0=BB=D0=B0=D0=B9=20=D0=94=D0=B0?= =?UTF-8?q?=D0=BD=D0=B0=D0=B8=D0=BB=D0=BE=D0=B2?= Date: Tue, 19 May 2020 13:04:33 +0300 Subject: [PATCH] Mistaken indexes fix --- Exercise8/exercise8.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Exercise8/exercise8.ipynb b/Exercise8/exercise8.ipynb index 8cd6824..d8aeda3 100755 --- a/Exercise8/exercise8.ipynb +++ b/Exercise8/exercise8.ipynb @@ -683,7 +683,7 @@ "\n", "$$ \\frac{\\partial J}{\\partial x_k^{(i)}} = \\sum_{j:r(i,j)=1} \\left( \\left(\\theta^{(j)}\\right)^T x^{(i)} - y^{(i,j)} \\right) \\theta_k^{(j)} $$\n", "\n", - "$$ \\frac{\\partial J}{\\partial \\theta_k^{(j)}} = \\sum_{i:r(i,j)=1} \\left( \\left(\\theta^{(j)}\\right)^T x^{(i)}- y^{(i,j)} \\right) x_k^{(j)} $$\n", + "$$ \\frac{\\partial J}{\\partial \\theta_k^{(j)}} = \\sum_{i:r(i,j)=1} \\left( \\left(\\theta^{(j)}\\right)^T x^{(i)}- y^{(i,j)} \\right) x_k^{(i)} $$\n", "\n", "Note that the function returns the gradient for both sets of variables by unrolling them into a single vector. After you have completed the code to compute the gradients, the next cell run a gradient check\n", "(available in `utils.checkCostFunction`) to numerically check the implementation of your gradients (this is similar to the numerical check that you used in the neural networks exercise. If your implementation is correct, you should find that the analytical and numerical gradients match up closely.\n", @@ -809,7 +809,7 @@ "\n", "$$ \\frac{\\partial J}{\\partial x_k^{(i)}} = \\sum_{j:r(i,j)=1} \\left( \\left(\\theta^{(j)}\\right)^T x^{(i)} - y^{(i,j)} \\right) \\theta_k^{(j)} + \\lambda x_k^{(i)} $$\n", "\n", - "$$ \\frac{\\partial J}{\\partial \\theta_k^{(j)}} = \\sum_{i:r(i,j)=1} \\left( \\left(\\theta^{(j)}\\right)^T x^{(i)}- y^{(i,j)} \\right) x_k^{(j)} + \\lambda \\theta_k^{(j)} $$\n", + "$$ \\frac{\\partial J}{\\partial \\theta_k^{(j)}} = \\sum_{i:r(i,j)=1} \\left( \\left(\\theta^{(j)}\\right)^T x^{(i)}- y^{(i,j)} \\right) x_k^{(i)} + \\lambda \\theta_k^{(j)} $$\n", "\n", "This means that you just need to add $\\lambda x^{(i)}$ to the `X_grad[i,:]` variable described earlier, and add $\\lambda \\theta^{(j)}$ to the `Theta_grad[j, :]` variable described earlier.\n", "\n",