Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commit 650edf9

Browse files
Merge pull request GokuMohandas#73 from pawelnguyen/patch-1
Fix minor typo
2 parents 5dd242b + 5dbc75c commit 650edf9

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

‎notebooks/11_Convolutional_Neural_Networks.ipynb‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -99,7 +99,7 @@
9999
},
100100
"cell_type": "markdown",
101101
"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",
103103
"\n",
104104
"<img src=\"https://raw.githubusercontent.com/GokuMohandas/practicalAI/master/images/conv.gif\" width=400>"
105105
]
@@ -2208,4 +2208,4 @@
22082208
]
22092209
}
22102210
]
2211-
}
2211+
}

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /