commit 605819c866571627904beabc0ba1d309ac5a9439
parent 0220388672490820ac52c1a5565dfec5cc0d50d7
Author: Andrew <andrewlaack1@gmail.com>
Date: Tue, 25 Jun 2024 14:40:38 -0500
Took notes on CNN information
Diffstat:
3 files changed, 27 insertions(+), 0 deletions(-)
diff --git a/CNN.md b/CNN.md
@@ -0,0 +1,16 @@
+:ml:
+# Convolutional Neural Network
+
+ML SS
+
+## Notes
+
+**Definition:** A convolutional neural network is a neural network that has convolutional layers that perform filtering functions upon the input data.
+
+A convolution is the process of moving a filter across some data and calculating the current values based on the surrounding values multiplied by the values in the filter and then summing them for the final result.
+
+CNNs are good for image detection because they retain information about pixels and what surrounds them. This allows them to pick up edges, curves, and higher level concepts.
+
+When using CNNs it is a good idea to start at around 32 filters (or higher) and increase (often double) the number of filters as the layers progress.
+
+Additionally, don't forget to add [[MaxPooling.md]] to ensure features are compressed and complexity of the model is minimized.
diff --git a/MachineLearning.md b/MachineLearning.md
@@ -154,3 +154,4 @@ Concepts:
[[MaxNormRegularization.md]]
[[Tensor.md]]
[[Transpose.md]]
+[[CNN.md]]
diff --git a/MaxPooling.md b/MaxPooling.md
@@ -0,0 +1,10 @@
+:ml:
+# Max Pooling
+
+ML SS
+
+## Notes
+
+**Definition:** Max pooling is a processing technique whereby a pool size is selected (2x2 as an example) and the values in the pool are compressed into one value.
+
+This is a technique to both reduce computational complexity of a model and to extract higher level features.
