Skip to content

Changes to ex4 notebook #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Ognjen303 wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Changes to ex4 notebook #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c044f1d
Changed X to X.Transpose in ex4
Ognjen303 Aug 10, 2022
37e3bf9
Added Lecture 10 cs229-notes-deep_learning.pdf
Ognjen303 Aug 10, 2022
d1142ad
Changed image showing the number from X to X.T
Ognjen303 Aug 10, 2022
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
Binary file added ex4/Lecture 10 cs229-notes-deep_learning.pdf
View file
Open in desktop
Binary file not shown.
17 changes: 12 additions & 5 deletions ex4/PE4 - Learning Neural Networks (Exercises).ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
"\n",
"Load the data and view some samples in the same way as [ex3](https://github.com/rickwierenga/CS229-Python/tree/master/ex3).\n",
"\n",
"Remember the output of a neural network: $h_\\Theta(x) \\in \\mathbb{R}^K$. We want y to be a 2 dimensional vector in the form that are network should output. For example, we would represent the output 1 as:\n",
"Remember the output of a neural network: $h_\\Theta(x) \\in \\mathbb{R}^K$. We want y to be a K dimensional vector in the form that are network should output. For example, we would represent the output 1 as:\n",
"\n",
"$\\begin{bmatrix}0\\\\1\\\\0\\\\0\\\\0\\\\0\\\\0\\\\0\\\\0\\\\0\\end{bmatrix}$"
]
Expand Down Expand Up @@ -68,6 +68,13 @@
"y = data[\"y\"]\n",
"y = y.reshape(len(y))\n",
"\n",
"# ----------NOTE-----------------\n",
"# X should have training examples in columns, not rows\n",
"# Read also end of page 7 of 'Lecture 10 cs229-notes-deep_learning.pdf', where it says the same thing \n",
"# And also the function 'forward' assumes training examples are in columns\n",
"X = X.T\n",
"\n",
"\n",
"# Initialize some useful variables\n",
"m, n = X.shape\n",
"input_layer_size = 400\n",
Expand Down Expand Up @@ -112,7 +119,7 @@
"\n",
"# get 100 random images from the dataset\n",
"num_samples = 100\n",
"samples = random.sample(list(X), num_samples)\n",
"samples = random.sample(list(X.T), num_samples)\n",
"display_img = Image.new('RGB', (200, 200))\n",
"\n",
"# loop over the images, turn them into a PIL image\n",
Expand Down Expand Up @@ -168,7 +175,7 @@
" return 1 / (1 + np.exp(-z))\n",
"\n",
"def add_bias(X):\n",
" m = len(X)\n",
" m = X.shape[1]\n",
" bias = np.ones(m)\n",
" X = np.vstack((bias, X.T)).T\n",
" return X\n",
Expand Down Expand Up @@ -670,7 +677,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
Expand All @@ -684,7 +691,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.9.7"
}
},
"nbformat": 4,
Expand Down