You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: notebooks/11_Convolutional_Neural_Networks.ipynb
+2-2Lines changed: 2 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -99,7 +99,7 @@
99
99
},
100
100
"cell_type": "markdown",
101
101
"source": [
102
-
"At the core of CNNs are filters (weights, kernels, etc.) which convolve (slide) across our input to extract relevante features. The filters are initialized randomly but learn to pick up meaningful features from the input that aid in optimizing for the objective. We're going to teach CNNs in an unorthodox method where we entirely focus on applying it to 2D text data. Each input is composed of words and we will be representing each word as one-hot encoded vector which gives us our 2D input. The intuition here is that each filter represents a feature and we will use this filter on other inputs to capture the same feature. This is known as parameter sharing.\n",
102
+
"At the core of CNNs are filters (weights, kernels, etc.) which convolve (slide) across our input to extract relevant features. The filters are initialized randomly but learn to pick up meaningful features from the input that aid in optimizing for the objective. We're going to teach CNNs in an unorthodox method where we entirely focus on applying it to 2D text data. Each input is composed of words and we will be representing each word as one-hot encoded vector which gives us our 2D input. The intuition here is that each filter represents a feature and we will use this filter on other inputs to capture the same feature. This is known as parameter sharing.\n",
0 commit comments